Publications

• [ 2023 ]
• [ 2022 ]
• [ 2021 ]
• [ 2020 ]
• [ 2019 ]
• [ 2018 ]
• [ 2017 ]
• [ 2016 ]
• [ 2015 ]
• [ 2014 ]
• [ 2013 ]
• [ 2012 ]
• [ 2011 ]
• [ 2010 ]
• [ 2009 (to appear) ]
• [ 2009 ]
• [ 2008 ]
• [ 2007 ]
• [ 2006 ]
• [ 2005 ]
• [ 2004 ]
• [ 2003 ]
• [ 2002 ]
• [ 2001 ]
• [ 2000 ]
• [ 1999 ]
• [ 1998 ]
• [ 1997 ]
• [ 1996 ]
• [ 1995 ]
• [ 1994 ]
• [ 1993 ]
• [ 1992 ]
• [ 1991 ]
• [ 1990 ]
• [ 1989 ]
• [ 1988 ]
• [ 1987 ]
• [ 1986 ]
• [ 1985 ]
• [ 1984 ]
• [ 1983 ]

• 
  Synoptische Interfaces Digitaler Editionen Herbst, Yannik; Roeder, Torsten; Reul, Christian in DHd2023: Open Humanities, Open Culture (2023).
  • [ BibTeX ]
  • [ URL ]
  @article{herbst2023synoptische, author = {Herbst, Yannik and Roeder, Torsten and Reul, Christian}, journal = {DHd2023: Open Humanities, Open Culture}, keywords = {myown}, title = {Synoptische Interfaces Digitaler Editionen}, year = 2023 }
• 
  Algorithmen-gestützte Analyse visuell-materieller Eigenschaften von Briefen Nantke, Julia; Reul, Christian; Bläß, Sandra; Flüh, Marie in DHd2023: Open Humanities, Open Culture (2023).
  • [ BibTeX ]
  • [ URL ]
  @article{nantke2023algorithmengesttzte, author = {Nantke, Julia and Reul, Christian and Bläß, Sandra and Flüh, Marie}, journal = {DHd2023: Open Humanities, Open Culture}, keywords = {myown}, title = {Algorithmen-gestützte Analyse visuell-materieller Eigenschaften von Briefen}, year = 2023 }
• 
  Analyse, Produktion, Reflexion: Nachnutzungsszenarien für Forschungsdaten am Beispiel der Daten des Projekts Dehmel digital Bläß, Sandra; Flüh, Marie; Nantke, Julia; Reul, Christian in DHd2023: Open Humanities, Open Culture (2023).
  • [ BibTeX ]
  • [ URL ]
  @article{blass2023analyse, author = {Bläß, Sandra and Flüh, Marie and Nantke, Julia and Reul, Christian}, journal = {DHd2023: Open Humanities, Open Culture}, keywords = {myown}, title = {Analyse, Produktion, Reflexion: Nachnutzungsszenarien für Forschungsdaten am Beispiel der Daten des Projekts Dehmel digital}, year = 2023 }

• 
  Handwritten Text Recognition und Word Mover’s Distance als Grundlagen der digitalen Edition "Die Kindheit Jesu Konrads von Fußesbrunnen" Tomasek, Stefan; Reul, Christian; Wehner, Maximilian in DHd2022: Kulturen des digitalen Gedächtnisses (2022).
  • [ BibTeX ]
  • [ URL ]
  @article{tomasek2022handwritten, author = {Tomasek, Stefan and Reul, Christian and Wehner, Maximilian}, journal = {DHd2022: Kulturen des digitalen Gedächtnisses}, keywords = {myown}, title = {Handwritten Text Recognition und Word Mover’s Distance als Grundlagen der digitalen Edition "Die Kindheit Jesu Konrads von Fußesbrunnen"}, year = 2022 }
• 
  Querying a Clinical Data Warehouse for Combinations of Clinical and Imaging Data Kaspar, Mathias; Liman, Leon; Morbach, Caroline; Dietrich, Georg; Seidlmayer, Lea Katharina; Puppe, Frank; Störk, Stefan in Journal of Digital Imaging (2022).
  • [ BibTeX ]
  • [ URL ]
  @article{Kaspar_2022, author = {Kaspar, Mathias and Liman, Leon and Morbach, Caroline and Dietrich, Georg and Seidlmayer, Lea Katharina and Puppe, Frank and Störk, Stefan}, journal = {Journal of Digital Imaging}, keywords = {myown}, month = {nov}, publisher = {Springer Science and Business Media {LLC}}, title = {Querying a Clinical Data Warehouse for Combinations of Clinical and Imaging Data}, year = 2022 }
• 
  Conflict Handling in Product Configuration using Answer Set Programming Herud, Konstantin; Baumeister, Joachim; Sabuncu, Orkunt; Schaub, Torsten in ICLP Workshop Answer Set Programming and Other Computing Paradigms (2022).
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  @inproceedings{hbs:22, author = {Herud, Konstantin and Baumeister, Joachim and Sabuncu, Orkunt and Schaub, Torsten}, booktitle = {ICLP Workshop Answer Set Programming and Other Computing Paradigms}, keywords = {myown}, title = {Conflict Handling in Product Configuration using Answer Set Programming}, year = 2022 }
• 
  OCR4all - Massenvolltextdigitalisierung von Drucken mithilfe von OCR-D und hochqualitative Transkription von Handschriften Langhanki, Florian; Wehner, Maximilian; Baierer, Konstantin; Hinrichsen, Lena; Reul, Christian in DHd2022: Kulturen des digitalen Gedächtnisses (2022).
  • [ BibTeX ]
  • [ URL ]
  @article{langhanki2022ocr4all, author = {Langhanki, Florian and Wehner, Maximilian and Baierer, Konstantin and Hinrichsen, Lena and Reul, Christian}, journal = {DHd2022: Kulturen des digitalen Gedächtnisses}, keywords = {myown}, title = {OCR4all - Massenvolltextdigitalisierung von Drucken mithilfe von OCR-D und hochqualitative Transkription von Handschriften}, year = 2022 }
• 
  Structured, Harmonized, and Interoperable Integration of Clinical Routine Data to Compute Heart Failure Risk Scores Sommer, Kim K.; Amr, Ali; Bavendiek, Udo; Beierle, Felix; Brunecker, Peter; Dathe, Henning; Eils, Jürgen; Ertl, Maximilian; Fette, Georg; Gietzelt, Matthias; Heidecker, Bettina; Hellenkamp, Kristian; Heuschmann, Peter; Hoos, Jennifer D. E.; Kesztyüs, Tibor; Kerwagen, Fabian; Kindermann, Aljoscha; Krefting, Dagmar; Landmesser, Ulf; Marschollek, Michael; Meder, Benjamin; Merzweiler, Angela; Prasser, Fabian; Pryss, Rüdiger; Richter, Jendrik; Schneider, Philipp; Störk, Stefan; Dieterich, Christoph in Life, (P. W. Dabrowski, ed.) (2022). 12(5)(749)
  • [ BibTeX ]
  • [ URL ]
  @article{sommer2022structured, author = {Sommer, Kim K. and Amr, Ali and Bavendiek, Udo and Beierle, Felix and Brunecker, Peter and Dathe, Henning and Eils, Jürgen and Ertl, Maximilian and Fette, Georg and Gietzelt, Matthias and Heidecker, Bettina and Hellenkamp, Kristian and Heuschmann, Peter and Hoos, Jennifer D. E. and Kesztyüs, Tibor and Kerwagen, Fabian and Kindermann, Aljoscha and Krefting, Dagmar and Landmesser, Ulf and Marschollek, Michael and Meder, Benjamin and Merzweiler, Angela and Prasser, Fabian and Pryss, Rüdiger and Richter, Jendrik and Schneider, Philipp and Störk, Stefan and Dieterich, Christoph}, editor = {Dabrowski, Piotr Wojtek}, journal = {Life}, keywords = {myown}, number = 749, title = {Structured, Harmonized, and Interoperable Integration of Clinical Routine Data to Compute Heart Failure Risk Scores}, volume = {12(5)}, year = 2022 }
• 
  Layered drawing of undirected graphs with generalized port constraints Zink, Johannes; Walter, Julian; Baumeister, Joachim; Wolff, Alexander in Computational Geometry: Theory and Applications (2022). 105-106 101886.
  • [ Abstract ]
  • [ BibTeX ]
  The aim of this research is a practical method to draw cable plans of complex machines. Such plans consist of electronic components and cables connecting specific ports of the components. Since the machines are configured for each client individually, cable plans need to be drawn automatically. The drawings must be well readable so that technicians can use them to debug the machines. In order to model plug sockets, we introduce port groups; within a group, ports can change their position (which we use to improve the aesthetics of the layout), but together the ports of a group must form a contiguous block. We approach the problem of drawing such cable plans by extending the well-known Sugiyama framework such that it incorporates ports and port groups. Since the framework assumes directed graphs, we propose several ways to orient the edges of the given undirected graph. We compare these methods experimentally, both on real-world data and synthetic data that carefully simulates real-world data. We measure the aesthetics of the resulting drawings by counting bends and crossings. Using these metrics, we experimentally compare our approach to Kieler JVLC 2014, a library for drawing graphs in the presence of port constraints. Our method produced 10--30 \% fewer crossings, while it performed equally well or slightly worse than Kieler with respect to the number of bends and the time used to compute a drawing.

  @article{ZINK2022101886, abstract = {The aim of this research is a practical method to draw cable plans of complex machines. Such plans consist of electronic components and cables connecting specific ports of the components. Since the machines are configured for each client individually, cable plans need to be drawn automatically. The drawings must be well readable so that technicians can use them to debug the machines. In order to model plug sockets, we introduce port groups; within a group, ports can change their position (which we use to improve the aesthetics of the layout), but together the ports of a group must form a contiguous block. We approach the problem of drawing such cable plans by extending the well-known Sugiyama framework such that it incorporates ports and port groups. Since the framework assumes directed graphs, we propose several ways to orient the edges of the given undirected graph. We compare these methods experimentally, both on real-world data and synthetic data that carefully simulates real-world data. We measure the aesthetics of the resulting drawings by counting bends and crossings. Using these metrics, we experimentally compare our approach to Kieler JVLC 2014, a library for drawing graphs in the presence of port constraints. Our method produced 10–30 \% fewer crossings, while it performed equally well or slightly worse than Kieler with respect to the number of bends and the time used to compute a drawing.}, author = {Zink, Johannes and Walter, Julian and Baumeister, Joachim and Wolff, Alexander}, journal = {Computational Geometry: Theory and Applications}, keywords = {rokt}, pages = 101886, title = {Layered drawing of undirected graphs with generalized port constraints}, volume = {105-106}, year = 2022 }
• 
  Automated provision of clinical routine data for a complex clinical follow-up study: A data warehouse solution Kaspar, Mathias; Fette, Georg; Hanke, Monika; Ertl, Maximilian; Puppe, Frank; Störk, Stefan in Health Informatics Journal, (P. Bamidis, ed.) (2022). 28(1)
  • [ BibTeX ]
  • [ URL ]
  @article{kaspar2022automated, author = {Kaspar, Mathias and Fette, Georg and Hanke, Monika and Ertl, Maximilian and Puppe, Frank and Störk, Stefan}, editor = {Bamidis, Panagiotis}, journal = {Health Informatics Journal}, keywords = {myown}, month = 1, number = 1, title = {Automated provision of clinical routine data for a complex clinical follow-up study: A data warehouse solution}, volume = 28, year = 2022 }
• 
  {Adapting Coreference Algorithms to German Fairy Tales} Schmidt, David; Krug, Markus; Puppe, Frank in Proceedings of the DHd 2022, M. Geierhos, P. Trilcke, I. Börner, S. Seifert, A. Busch, P. Helling (eds.) (2022).
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{schmidt_david_2022_6328165, author = {Schmidt, David and Krug, Markus and Puppe, Frank}, booktitle = {Proceedings of the DHd 2022}, editor = {Geierhos, Michaela and Trilcke, Peer and Börner, Ingo and Seifert, Sabine and Busch, Anna and Helling, Patrick}, keywords = {myown}, month = {mar}, publisher = {Zenodo}, title = {{Adapting Coreference Algorithms to German Fairy Tales}}, year = 2022 }
• 
  Open Source Handwritten Text Recognition on Medieval Manuscripts using Mixed Models and Document-Specific Finetuning Reul, Christian; Tomasek, Stefan; Langhanki, Florian; Springmann, Uwe in 2022 15th IAPR International Workshop on Document Analysis Systems (2022).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  This paper deals with the task of practical and open source Handwritten Text Recognition (HTR) on German medieval manuscripts. We report on our efforts to construct mixed recognition models which can be applied out-of-the-box without any further document-specific training but also serve as a starting point for finetuning by training a new model on a few pages of transcribed text (ground truth). To train the mixed models we collected a corpus of 35 manuscripts and ca. 12.5k text lines for two widely used handwriting styles, Gothic and Bastarda cursives. Evaluating the mixed models out-of-the-box on four unseen manuscripts resulted in an average Character Error Rate (CER) of 6.22%. After training on 2, 4 and eventually 32 pages the CER dropped to 3.27%, 2.58%, and 1.65%, respectively. While the in-domain recognition and training of models (Bastarda model to Bastarda material, Gothic to Gothic) unsurprisingly yielded the best results, finetuning out-of-domain models to unseen scripts was still shown to be superior to training from scratch. Our new mixed models have been made openly available to the community.

  @article{reul2022source, abstract = {This paper deals with the task of practical and open source Handwritten Text Recognition (HTR) on German medieval manuscripts. We report on our efforts to construct mixed recognition models which can be applied out-of-the-box without any further document-specific training but also serve as a starting point for finetuning by training a new model on a few pages of transcribed text (ground truth). To train the mixed models we collected a corpus of 35 manuscripts and ca. 12.5k text lines for two widely used handwriting styles, Gothic and Bastarda cursives. Evaluating the mixed models out-of-the-box on four unseen manuscripts resulted in an average Character Error Rate (CER) of 6.22%. After training on 2, 4 and eventually 32 pages the CER dropped to 3.27%, 2.58%, and 1.65%, respectively. While the in-domain recognition and training of models (Bastarda model to Bastarda material, Gothic to Gothic) unsurprisingly yielded the best results, finetuning out-of-domain models to unseen scripts was still shown to be superior to training from scratch. Our new mixed models have been made openly available to the community.}, author = {Reul, Christian and Tomasek, Stefan and Langhanki, Florian and Springmann, Uwe}, journal = {2022 15th IAPR International Workshop on Document Analysis Systems}, keywords = {myown:selected}, title = {Open Source Handwritten Text Recognition on Medieval Manuscripts using Mixed Models and Document-Specific Finetuning}, year = 2022 }
• 
  Semantische Tiefenerschließung historischer Lexika mittels Text- und Typographieerkennung Reul, Christian in Ursula Rautenberg/Anja Voeste (Hgg.): Typographie. Theoretische Konzeptionen, historische Perspektiven, künstlerische Applikationen (2022).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  Bei der Konvertierung typographisch komplexer Textvorlagen in eine elektronische Form stellt die rein textuelle Erfassung, z. B. mittels Optical Character Recognition (OCR), häufig nur den ersten Bearbeitungsschritt dar. Um die logische Struktur solcher Texte zu erschließen, ist zudem eine präzise automatische Erkennung der enthaltenen typographischen Attribute nötig. Dieser Artikel stellt eine Methode vor, die durch Training einer frei verfügbaren Texterkennungssoftware eine feinkörnige Klassifikation typographischer Auszeichnungsmittel ermöglicht und die so gewonnenen semantischen Informationen auf das Ergebnis der textuellen Erkennung abbildet. Als Anwendungsbeispiel dient Daniel Sanders‘ Wörterbuch der Deutschen Sprache, in dem der Typographie eine besonders wichtige und komplexe semantische Funktion zukommt.

  @article{reul2021semantische, abstract = {Bei der Konvertierung typographisch komplexer Textvorlagen in eine elektronische Form stellt die rein textuelle Erfassung, z. B. mittels Optical Character Recognition (OCR), häufig nur den ersten Bearbeitungsschritt dar. Um die logische Struktur solcher Texte zu erschließen, ist zudem eine präzise automatische Erkennung der enthaltenen typographischen Attribute nötig. Dieser Artikel stellt eine Methode vor, die durch Training einer frei verfügbaren Texterkennungssoftware eine feinkörnige Klassifikation typographischer Auszeichnungsmittel ermöglicht und die so gewonnenen semantischen Informationen auf das Ergebnis der textuellen Erkennung abbildet. Als Anwendungsbeispiel dient Daniel Sanders‘ Wörterbuch der Deutschen Sprache, in dem der Typographie eine besonders wichtige und komplexe semantische Funktion zukommt.}, author = {Reul, Christian}, journal = {Ursula Rautenberg/Anja Voeste (Hgg.): Typographie. Theoretische Konzeptionen, historische Perspektiven, künstlerische Applikationen}, keywords = {myown}, title = {Semantische Tiefenerschließung historischer Lexika mittels Text- und Typographieerkennung}, year = 2022 }

• 
  Rule-based Semantic Relation Extraction in Regulatory Documents Korger, Andreas; Baumeister, Joachim in Learning. Knowledge. Data. Analytics (2021).
  • [ BibTeX ]
  • [ Download ]
  @inproceedings{Korger2021, address = {Munich, Germany}, author = {Korger, Andreas and Baumeister, Joachim}, booktitle = {Learning. Knowledge. Data. Analytics}, keywords = {rokt}, month = {September}, title = {Rule-based Semantic Relation Extraction in Regulatory Documents}, year = 2021 }
• 
  Calculating Key Figures for Radiology Departments Using a Clinical Data Warehouse – A Technical Case Report Liman, Leon; Fette, Georg; Krebs, Jonathan; Puppe, Frank in Studies in Health Technology and Informatics (2021). 283 69–77.
  • [ BibTeX ]
  @article{liman2021calculating, author = {Liman, Leon and Fette, Georg and Krebs, Jonathan and Puppe, Frank}, journal = {Studies in Health Technology and Informatics}, keywords = {myown}, pages = {69 - 77}, title = {Calculating Key Figures for Radiology Departments Using a Clinical Data Warehouse – A Technical Case Report}, volume = 283, year = 2021 }
• 
  OCR-D & OCR4all: Two Complementary Approaches for Improved OCR of Historical Sources Baierer, Konstantin; Büttner, Andreas; Engl, Elisabeth; Hinrichsen, Lena; Reul, Christian in 6th International Workshop on Computational History (2021).
  • [ Abstract ]
  • [ BibTeX ]
  In order to leverage recent advances within the field of computer science for tasks ranging from full text search to various forms of quantitative analysis, an important desideratum in many areas of historical research is the availability of sources in the form of machine-actionable text. Here we present two complementary and free-to-use approaches, OCR-D and OCR4all. They deal with the conversion of scanned historical documents into such machine-actionable text and allow to tackle a variety of different use cases with diverse user requirements regarding both quantity and quality.

  @article{baierer2021ocr4all, abstract = {In order to leverage recent advances within the field of computer science for tasks ranging from full text search to various forms of quantitative analysis, an important desideratum in many areas of historical research is the availability of sources in the form of machine-actionable text. Here we present two complementary and free-to-use approaches, OCR-D and OCR4all. They deal with the conversion of scanned historical documents into such machine-actionable text and allow to tackle a variety of different use cases with diverse user requirements regarding both quantity and quality.}, author = {Baierer, Konstantin and Büttner, Andreas and Engl, Elisabeth and Hinrichsen, Lena and Reul, Christian}, journal = {6th International Workshop on Computational History}, keywords = {myown}, title = {OCR-D & OCR4all: Two Complementary Approaches for Improved OCR of Historical Sources}, year = 2021 }
• 
  Calculating Key Figures for Radiology Departments Using a Clinical Data Warehouse – A Technical Case Report Liman, Leon; Fette, Georg; Krebs, Jonathan; Puppe, Frank in Studies in Health Technology and Informatics (2021). 283 69–77.
  • [ BibTeX ]
  @article{liman2021calculating, author = {Liman, Leon and Fette, Georg and Krebs, Jonathan and Puppe, Frank}, journal = {Studies in Health Technology and Informatics}, keywords = {myown}, pages = {69 - 77}, title = {Calculating Key Figures for Radiology Departments Using a Clinical Data Warehouse – A Technical Case Report}, volume = 283, year = 2021 }
• 
  Mixed Model OCR Training on Historical Latin Script for Out-of-the-Box Recognition and Finetuning Reul, Christian; Wick, Christoph; Nöth, Maximilian; Büttner, Andreas; Wehner, Maximilian; Springmann, Uwe in 6th International Workshop on Historical Document Imaging and Processing (2021).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  In order to apply Optical Character Recognition (OCR) to historical printings of Latin script fully automatically, we report on our efforts to construct a widely-applicable polyfont recognition model yielding text with a Character Error Rate (CER) around 2% when applied out-of-the-box. Moreover, we show how this model can be further finetuned to specific classes of printings with little manual and computational effort. The mixed or polyfont model is trained on a wide variety of materials, in terms of age (from the 15th to the 19th century), typography (various types of Fraktur and Antiqua), and languages (among others, German, Latin, and French). To optimize the results we combined established techniques of OCR training like pretraining, data augmentation, and voting. In addition, we used various preprocessing methods to enrich the training data and obtain more robust models. We also implemented a two-stage approach which first trains on all available, considerably unbalanced data and then refines the output by training on a selected more balanced subset. Evaluations on 29 previously unseen books resulted in a CER of 1.73%, outperforming a widely used standard model with a CER of 2.84% by almost 40%. Training a more specialized model for some unseen Early Modern Latin books starting from our mixed model led to a CER of 1.47%, an improvement of up to 50% compared to training from scratch and up to 30% compared to training from the aforementioned standard model. Our new mixed model is made openly available to the community.

  @article{reul2021mixed, abstract = {In order to apply Optical Character Recognition (OCR) to historical printings of Latin script fully automatically, we report on our efforts to construct a widely-applicable polyfont recognition model yielding text with a Character Error Rate (CER) around 2% when applied out-of-the-box. Moreover, we show how this model can be further finetuned to specific classes of printings with little manual and computational effort. The mixed or polyfont model is trained on a wide variety of materials, in terms of age (from the 15th to the 19th century), typography (various types of Fraktur and Antiqua), and languages (among others, German, Latin, and French). To optimize the results we combined established techniques of OCR training like pretraining, data augmentation, and voting. In addition, we used various preprocessing methods to enrich the training data and obtain more robust models. We also implemented a two-stage approach which first trains on all available, considerably unbalanced data and then refines the output by training on a selected more balanced subset. Evaluations on 29 previously unseen books resulted in a CER of 1.73%, outperforming a widely used standard model with a CER of 2.84% by almost 40%. Training a more specialized model for some unseen Early Modern Latin books starting from our mixed model led to a CER of 1.47%, an improvement of up to 50% compared to training from scratch and up to 30% compared to training from the aforementioned standard model. Our new mixed model is made openly available to the community.}, author = {Reul, Christian and Wick, Christoph and Nöth, Maximilian and Büttner, Andreas and Wehner, Maximilian and Springmann, Uwe}, journal = {6th International Workshop on Historical Document Imaging and Processing}, keywords = {myown:selected}, title = {Mixed Model OCR Training on Historical Latin Script for Out-of-the-Box Recognition and Finetuning}, year = 2021 }
• 
  One-Model Ensemble-Learning for Text Recognition of Historical Printings Wick, Christoph; Reul, Christian in Proceedings of the 16th International Conference on Document Analysis and Recognition ICDAR 2021 (2021).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  In this paper, we propose a novel method for Automatic Text Recognition (ATR) on early printed books. Our approach signi�cantly reduces the Character Error Rates (CERs) for book-speci�c training when only a few lines of Ground Truth (GT) are available and considerably outperforms previous methods. An ensemble of models is trained simultaneously by optimising each one independently but also with respect to a fused output obtained by averaging the individual con�dence matrices. Various experiments on �ve early printed books show that this approach already outperforms the current state-of-the-art by up to 20% and 10% on average. Replacing the averaging of the con�dence matrices during prediction with a con�dence-based voting boosts our results by an additional 8% leading to a total average improvement of about 17%.

  @article{wick2021onemodel, abstract = {In this paper, we propose a novel method for Automatic Text Recognition (ATR) on early printed books. Our approach signi�cantly reduces the Character Error Rates (CERs) for book-speci�c training when only a few lines of Ground Truth (GT) are available and considerably outperforms previous methods. An ensemble of models is trained simultaneously by optimising each one independently but also with respect to a fused output obtained by averaging the individual con�dence matrices. Various experiments on �ve early printed books show that this approach already outperforms the current state-of-the-art by up to 20% and 10% on average. Replacing the averaging of the con�dence matrices during prediction with a con�dence-based voting boosts our results by an additional 8% leading to a total average improvement of about 17%.}, author = {Wick, Christoph and Reul, Christian}, booktitle = {Proceedings of the 16th International Conference on Document Analysis and Recognition ICDAR 2021}, keywords = {myown:selected}, title = {One-Model Ensemble-Learning for Text Recognition of Historical Printings}, year = 2021 }
• 
  The {F}airy{N}et Corpus - Character Networks for {G}erman Fairy Tales Schmidt, David; Zehe, Albin; Lorenzen, Janne; Sergel, Lisa; D{\"u}ker, Sebastian; Krug, Markus; Puppe, Frank in Proceedings of the 5th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (2021). 49–56.
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  This paper presents a data set of German fairy tales, manually annotated with character networks which were obtained with high inter rater agreement. The release of this corpus provides an opportunity of training and comparing different algorithms for the extraction of character networks, which so far was barely possible due to heterogeneous interests of previous researchers. We demonstrate the usefulness of our data set by providing baseline experiments for the automatic extraction of character networks, applying a rule-based pipeline as well as a neural approach, and find the neural approach outperforming the rule-approach in most evaluation settings.

  @inproceedings{schmidt-etal-2021-fairynet, abstract = {This paper presents a data set of German fairy tales, manually annotated with character networks which were obtained with high inter rater agreement. The release of this corpus provides an opportunity of training and comparing different algorithms for the extraction of character networks, which so far was barely possible due to heterogeneous interests of previous researchers. We demonstrate the usefulness of our data set by providing baseline experiments for the automatic extraction of character networks, applying a rule-based pipeline as well as a neural approach, and find the neural approach outperforming the rule-approach in most evaluation settings.}, address = {Punta Cana, Dominican Republic (online)}, author = {Schmidt, David and Zehe, Albin and Lorenzen, Janne and Sergel, Lisa and D{\"u}ker, Sebastian and Krug, Markus and Puppe, Frank}, booktitle = {Proceedings of the 5th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature}, keywords = {myown}, month = {nov}, pages = {49–56}, publisher = {Association for Computational Linguistics}, title = {The {F}airy{N}et Corpus - Character Networks for {G}erman Fairy Tales}, year = 2021 }
• 
  Detecting Scenes in Fiction: A new Segmentation Task Zehe, Albin; Konle, Leonard; Dümpelmann, Lea; Gius, Evelyn; Hotho, Andreas; Jannidis, Fotis; Kaufmann, Lucas; Krug, Markus; Puppe, Frank; Reiter, Nils; Schreiber, Annekea; Wiedmer, Nathalie in Proceedings of the 16th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 1, Long Papers (2021).
  • [ BibTeX ]
  @inproceedings{zehe2021detecting, author = {Zehe, Albin and Konle, Leonard and Dümpelmann, Lea and Gius, Evelyn and Hotho, Andreas and Jannidis, Fotis and Kaufmann, Lucas and Krug, Markus and Puppe, Frank and Reiter, Nils and Schreiber, Annekea and Wiedmer, Nathalie}, booktitle = {Proceedings of the 16th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 1, Long Papers}, keywords = {task}, publisher = {ACL}, title = {Detecting Scenes in Fiction: A new Segmentation Task}, year = 2021 }

• 
  Unlocking the PACS DICOM Domain for its Use in Clinical Research Data Warehouses. Kaspar, Mathias; Liman, Leon; Ertl, Maximilian; Fette, Georg; Seidlmayer, Lea Katharina; Schreiber, Laura; Puppe, Frank; Störk, Stefan in J. Digit. Imaging (2020). 33(4) 1016–1025.
  • [ BibTeX ]
  • [ URL ]
  @article{journals/jdi/KasparLEFSSPS20, author = {Kaspar, Mathias and Liman, Leon and Ertl, Maximilian and Fette, Georg and Seidlmayer, Lea Katharina and Schreiber, Laura and Puppe, Frank and Störk, Stefan}, journal = {J. Digit. Imaging}, keywords = {myown}, number = 4, pages = {1016-1025}, title = {Unlocking the PACS DICOM Domain for its Use in Clinical Research Data Warehouses.}, volume = 33, year = 2020 }
• 
  Integrating user-specified Knowledge for semi-automatic Coreference Resolution Schmidt, David; Krug, Markus; Puppe, Frank (2020).
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{schmidt2020integrating, author = {Schmidt, David and Krug, Markus and Puppe, Frank}, keywords = {myown}, month = {feb}, organization = {Verband Digital Humanities im deutschsprachigen Raum}, title = {Integrating user-specified Knowledge for semi-automatic Coreference Resolution}, year = 2020 }
• 
  Translating openEHR Models to FHIR. Fette, Georg; Ertl, Max; Störk, Stefan in MIE, Studies in Health Technology and Informatics, L. B. Pape-Haugaard, C. Lovis, I. C. Madsen, P. Weber, P. H. Nielsen, P. Scott (eds.) (2020). (Vol. 270) 1415–1416.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{conf/mie/FetteES20, author = {Fette, Georg and Ertl, Max and Störk, Stefan}, booktitle = {MIE}, crossref = {conf/mie/2020}, editor = {Pape-Haugaard, Louise Bilenberg and Lovis, Christian and Madsen, Inge Cort and Weber, Patrick and Nielsen, Per Hostrup and Scott, Philip}, keywords = {myown}, note = {Conference cancelled because of Covid-19.}, pages = {1415-1416}, publisher = {IOS Press}, series = {Studies in Health Technology and Informatics}, title = {Translating openEHR Models to FHIR.}, volume = 270, year = 2020 }
• 
  Coagulation factor XIII activity predicts left ventricular remodelling after acute myocardial infarction Frey, Anna; Gassenmaier, Tobias; Hofmann, Ulrich; Schmitt, Dominik; Fette, Georg; Marx, Almuth; Herterich, Sabine; Boivin‐Jahns, Valérie; Ertl, Georg; Bley, Thorsten; Frantz, Stefan; Jahns, Roland; Störk, Stefan in ESC heart failure (2020). 7(5) 2354–2364.
  • [ BibTeX ]
  @article{frey2020coagulation, author = {Frey, Anna and Gassenmaier, Tobias and Hofmann, Ulrich and Schmitt, Dominik and Fette, Georg and Marx, Almuth and Herterich, Sabine and Boivin‐Jahns, Valérie and Ertl, Georg and Bley, Thorsten and Frantz, Stefan and Jahns, Roland and Störk, Stefan}, journal = {ESC heart failure}, keywords = {myown}, month = 10, number = 5, pages = {2354-2364}, title = {Coagulation factor XIII activity predicts left ventricular remodelling after acute myocardial infarction}, volume = 7, year = 2020 }
• 
  Techniques for the Automatic Extraction of Character Networks in German Historic Novels Krug, Markus PhD thesis, Universit{\"a}t W{\"u}rzburg. (2020).
  • [ BibTeX ]
  @phdthesis{Krug2020, author = {Krug, Markus}, keywords = {myown}, school = {Universit{\"a}t W{\"u}rzburg}, title = {Techniques for the Automatic Extraction of Character Networks in German Historic Novels}, type = {doctoralthesis}, year = 2020 }
• 
  Case-Based Generation of Regulatory Documents and their Semantic Relatedness Korger, Andreas; Baumeister, Joachim in Proceedings of the Future of Information and Communications Conference (FICC) 2020, Advances in Intelligent Systems and Computing (2020).
  • [ BibTeX ]
  @inproceedings{korger2020casebased, address = {San Francisco.}, author = {Korger, Andreas and Baumeister, Joachim}, booktitle = {Proceedings of the Future of Information and Communications Conference (FICC) 2020}, keywords = {rokt}, month = {March}, publisher = {Springer}, series = {Advances in Intelligent Systems and Computing}, title = {Case-Based Generation of Regulatory Documents and their Semantic Relatedness}, year = 2020 }
• 
  Construction of a Corpus for the Evaluation of Textual Case-based Reasoning Architectures Korger, Andreas; Baumeister, Joachim in LWDA 2020 -- Lernen, Wissen, Daten, Analysen (2020).
  • [ BibTeX ]
  @inproceedings{KB:20, author = {Korger, Andreas and Baumeister, Joachim}, booktitle = {LWDA 2020 – Lernen, Wissen, Daten, Analysen}, keywords = {rokt}, title = {Construction of a Corpus for the Evaluation of Textual Case-based Reasoning Architectures}, year = 2020 }
• 
  Layered Drawing of Undirected Graphs with Generalized Port Constraints Walter, Julian; Zink, Johannes; Baumeister, Joachim; Wolff, Alexander in 28th International Symposium on Graph Drawing and Network Visualization (GD 2020) (2020).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  The aim of this research is a practical method to draw cable plans of complex machines. Such plans consist of electronic components and cables connecting specific ports of the components. Since the machines are configured for each client individually, cable plans need to be drawn automatically. The drawings must be well readable so that technicians can use them to debug the machines. In order to model plug sockets, we introduce port groups; within a group, ports can change their position (which we use to improve the aesthetics of the layout), but together the ports of a group must form a contiguous block. We approach the problem of drawing such cable plans by extending the well-known Sugiyama framework such that it incorporates ports and port groups. Since the framework assumes directed graphs, we propose several ways to orient the edges of the given undirected graph. We compare these methods experimentally, both on real-world data and synthetic data that carefully simulates real-world data. We measure the aesthetics of the resulting drawings by counting bends and crossings. Using these metrics, we compare our approach to Kieler [JVLC 2014], a library for drawing graphs in the presence of port constraints.

  @inproceedings{walter2020layered, abstract = {The aim of this research is a practical method to draw cable plans of complex machines. Such plans consist of electronic components and cables connecting specific ports of the components. Since the machines are configured for each client individually, cable plans need to be drawn automatically. The drawings must be well readable so that technicians can use them to debug the machines. In order to model plug sockets, we introduce port groups; within a group, ports can change their position (which we use to improve the aesthetics of the layout), but together the ports of a group must form a contiguous block. We approach the problem of drawing such cable plans by extending the well-known Sugiyama framework such that it incorporates ports and port groups. Since the framework assumes directed graphs, we propose several ways to orient the edges of the given undirected graph. We compare these methods experimentally, both on real-world data and synthetic data that carefully simulates real-world data. We measure the aesthetics of the resulting drawings by counting bends and crossings. Using these metrics, we compare our approach to Kieler [JVLC 2014], a library for drawing graphs in the presence of port constraints.}, author = {Walter, Julian and Zink, Johannes and Baumeister, Joachim and Wolff, Alexander}, booktitle = {28th International Symposium on Graph Drawing and Network Visualization (GD 2020)}, keywords = {rokt}, note = {cite arxiv:2008.10583}, title = {Layered Drawing of Undirected Graphs with Generalized Port Constraints}, year = 2020 }
• 
  Unlocking the PACS DICOM Domain for its Use in Clinical Research Data Warehouses. Kaspar, Mathias; Liman, Leon; Ertl, Maximilian; Fette, Georg; Seidlmayer, Lea Katharina; Schreiber, Laura; Puppe, Frank; Störk, Stefan in J. Digit. Imaging (2020). 33(4) 1016–1025.
  • [ BibTeX ]
  • [ URL ]
  @article{journals/jdi/KasparLEFSSPS20, author = {Kaspar, Mathias and Liman, Leon and Ertl, Maximilian and Fette, Georg and Seidlmayer, Lea Katharina and Schreiber, Laura and Puppe, Frank and Störk, Stefan}, journal = {J. Digit. Imaging}, keywords = {myown}, number = 4, pages = {1016-1025}, title = {Unlocking the PACS DICOM Domain for its Use in Clinical Research Data Warehouses.}, volume = 33, year = 2020 }
• 
  Calamari - A High-Performance Tensorflow-based Deep Learning Package for Optical Character Recognition Wick, Christoph; Reul, Christian; Puppe, Frank in Digital Humanities Quarterly (2020). 14(2)
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  Optical Character Recognition (OCR) on contemporary and historical data is still in the focus of many researchers. Especially historical prints require book specific trained OCR models to achieve applicable results [Springmann and Lüdeling 2017] [Reul et al. 2017a]. To reduce the human effort for manually annotating ground truth (GT) various techniques such as voting and pretraining have shown to be very efficient [Reul et al. 2018a] [Reul et al. 2018b]. Calamari is a new open source OCR line recognition software that both uses state-of-the art Deep Neural Networks (DNNs) implemented in Tensorflow and giving native support for techniques such as pretraining and voting. The customizable network architectures constructed of Convolutional Neural Networks (CNNS) and Long-Short-Term-Memory (LSTM) layers are trained by the so-called Connectionist Temporal Classification (CTC) algorithm of Graves et al. (2006). Optional usage of a GPU drastically reduces the computation times for both training and prediction. We use two different datasets to compare the performance of Calamari to OCRopy, OCRopus3, and Tesseract 4. Calamari reaches a Character Error Rate (CER) of 0.11% on the UW3 dataset written in modern English and 0.18% on the DTA19 dataset written in German Fraktur, which considerably outperforms the results of the existing softwares.

  @article{wick2020calamari, abstract = {Optical Character Recognition (OCR) on contemporary and historical data is still in the focus of many researchers. Especially historical prints require book specific trained OCR models to achieve applicable results [Springmann and Lüdeling 2017] [Reul et al. 2017a]. To reduce the human effort for manually annotating ground truth (GT) various techniques such as voting and pretraining have shown to be very efficient [Reul et al. 2018a] [Reul et al. 2018b]. Calamari is a new open source OCR line recognition software that both uses state-of-the art Deep Neural Networks (DNNs) implemented in Tensorflow and giving native support for techniques such as pretraining and voting. The customizable network architectures constructed of Convolutional Neural Networks (CNNS) and Long-Short-Term-Memory (LSTM) layers are trained by the so-called Connectionist Temporal Classification (CTC) algorithm of Graves et al. (2006). Optional usage of a GPU drastically reduces the computation times for both training and prediction. We use two different datasets to compare the performance of Calamari to OCRopy, OCRopus3, and Tesseract 4. Calamari reaches a Character Error Rate (CER) of 0.11% on the UW3 dataset written in modern English and 0.18% on the DTA19 dataset written in German Fraktur, which considerably outperforms the results of the existing softwares.}, author = {Wick, Christoph and Reul, Christian and Puppe, Frank}, journal = {Digital Humanities Quarterly}, keywords = {myown:selected}, number = 2, title = {Calamari - A High-Performance Tensorflow-based Deep Learning Package for Optical Character Recognition}, volume = 14, year = 2020 }

• 
  OCR4all - An Open-Source Tool Providing a (Semi-)Automatic OCR Workflow for Historical Printings Reul, Christian; Christ, Dennis; Hartelt, Alexander; Balbach, Nico; Wehner, Maximilian; Springmann, Uwe; Wick, Christoph; Grundig, Christine; Büttner, Andreas; Puppe, Frank in Applied Sciences (2019). 9(22)
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  Optical Character Recognition (OCR) on historical printings is a challenging task mainly due to the complexity of the layout and the highly variant typography. Nevertheless, in the last few years, great progress has been made in the area of historical OCR, resulting in several powerful open-source tools for preprocessing, layout analysis and segmentation, character recognition, and post-processing. The drawback of these tools often is their limited applicability by non-technical users like humanist scholars and in particular the combined use of several tools in a workflow. In this paper, we present an open-source OCR software called OCR4all, which combines state-of-the-art OCR components and continuous model training into a comprehensive workflow. While a variety of materials can already be processed fully automatically, books with more complex layouts require manual intervention by the users. This is mostly due to the fact that the required ground truth for training stronger mixed models (for segmentation, as well as text recognition) is not available, yet, neither in the desired quantity nor quality. To deal with this issue in the short run, OCR4all offers a comfortable GUI that allows error corrections not only in the final output, but already in early stages to minimize error propagations. In the long run, this constant manual correction produces large quantities of valuable, high quality training material, which can be used to improve fully automatic approaches. Further on, extensive configuration capabilities are provided to set the degree of automation of the workflow and to make adaptations to the carefully selected default parameters for specific printings, if necessary. During experiments, the fully automated application on 19th Century novels showed that OCR4all can considerably outperform the commercial state-of-the-art tool ABBYY Finereader on moderate layouts if suitably pretrained mixed OCR models are available. Furthermore, on very complex early printed books, even users with minimal or no experience were able to capture the text with manageable effort and great quality, achieving excellent Character Error Rates (CERs) below 0.5%. The architecture of OCR4all allows the easy integration (or substitution) of newly developed tools for its main components by standardized interfaces like PageXML, thus aiming at continual higher automation for historical printings.

  @article{reul2019ocr4all, abstract = {Optical Character Recognition (OCR) on historical printings is a challenging task mainly due to the complexity of the layout and the highly variant typography. Nevertheless, in the last few years, great progress has been made in the area of historical OCR, resulting in several powerful open-source tools for preprocessing, layout analysis and segmentation, character recognition, and post-processing. The drawback of these tools often is their limited applicability by non-technical users like humanist scholars and in particular the combined use of several tools in a workflow. In this paper, we present an open-source OCR software called OCR4all, which combines state-of-the-art OCR components and continuous model training into a comprehensive workflow. While a variety of materials can already be processed fully automatically, books with more complex layouts require manual intervention by the users. This is mostly due to the fact that the required ground truth for training stronger mixed models (for segmentation, as well as text recognition) is not available, yet, neither in the desired quantity nor quality. To deal with this issue in the short run, OCR4all offers a comfortable GUI that allows error corrections not only in the final output, but already in early stages to minimize error propagations. In the long run, this constant manual correction produces large quantities of valuable, high quality training material, which can be used to improve fully automatic approaches. Further on, extensive configuration capabilities are provided to set the degree of automation of the workflow and to make adaptations to the carefully selected default parameters for specific printings, if necessary. During experiments, the fully automated application on 19th Century novels showed that OCR4all can considerably outperform the commercial state-of-the-art tool ABBYY Finereader on moderate layouts if suitably pretrained mixed OCR models are available. Furthermore, on very complex early printed books, even users with minimal or no experience were able to capture the text with manageable effort and great quality, achieving excellent Character Error Rates (CERs) below 0.5%. The architecture of OCR4all allows the easy integration (or substitution) of newly developed tools for its main components by standardized interfaces like PageXML, thus aiming at continual higher automation for historical printings.}, author = {Reul, Christian and Christ, Dennis and Hartelt, Alexander and Balbach, Nico and Wehner, Maximilian and Springmann, Uwe and Wick, Christoph and Grundig, Christine and Büttner, Andreas and Puppe, Frank}, journal = {Applied Sciences}, keywords = {myown:selected}, number = 22, title = {OCR4all - An Open-Source Tool Providing a (Semi-)Automatic OCR Workflow for Historical Printings}, volume = 9, year = 2019 }
• 
  Ground Truth for training OCR engines on historical documents in German Fraktur and Early Modern Latin Springmann, Uwe; Reul, Christian; Dipper, Stefanie; Baiter, Johannes in JLCL: Special Issue on Automatic Text and Layout Recognition (2019).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  In this paper we describe a dataset of German and Latin ground truth (GT) for historical OCR in the form of printed text line images paired with their transcription. This dataset, called GT4HistOCR, consists of 313,173 line pairs covering a wide period of printing dates from incunabula from the 15th century to 19th century books printed in Fraktur types and is openly available under a CC-BY ⒋0 license. The special form of GT as line image/transcription pairs makes it directly usable to train state-of-the-art recognition models for OCR software employing recurring neural networks in LSTM architecture such as Tesseract 4 or OCRopus. We also provide some pretrained OCRopus models for subcorpora of our dataset yielding between 95% (early printings) and 98% (19th century Fraktur printings) character accuracy rates on unseen test cases, a Perl script to harmonize GT produced by different transcription rules, and give hints on how to construct GT for OCR purposes which has requirements that may differ from linguistically motivated transcriptions.

  @article{springmann2019ground, abstract = {In this paper we describe a dataset of German and Latin ground truth (GT) for historical OCR in the form of printed text line images paired with their transcription. This dataset, called GT4HistOCR, consists of 313,173 line pairs covering a wide period of printing dates from incunabula from the 15th century to 19th century books printed in Fraktur types and is openly available under a CC-BY ⒋0 license. The special form of GT as line image/transcription pairs makes it directly usable to train state-of-the-art recognition models for OCR software employing recurring neural networks in LSTM architecture such as Tesseract 4 or OCRopus. We also provide some pretrained OCRopus models for subcorpora of our dataset yielding between 95% (early printings) and 98% (19th century Fraktur printings) character accuracy rates on unseen test cases, a Perl script to harmonize GT produced by different transcription rules, and give hints on how to construct GT for OCR purposes which has requirements that may differ from linguistically motivated transcriptions.}, author = {Springmann, Uwe and Reul, Christian and Dipper, Stefanie and Baiter, Johannes}, journal = {JLCL: Special Issue on Automatic Text and Layout Recognition}, keywords = {myown}, title = {Ground Truth for training OCR engines on historical documents in German Fraktur and Early Modern Latin}, year = 2019 }
• 
  Automatic Semantic Text Tagging on Historical Lexica by Combining OCR and Typography Classification Reul, Christian; Göttel, Sebastian; Springmann, Uwe; Wick, Christoph; Würzner, Kay-Michael; Puppe, Frank in Proceedings of the 3rd International Conference on Digital Access to Textual Cultural Heritage (2019).
  • [ Abstract ]
  • [ BibTeX ]
  When converting historical lexica into electronic form the goal is not only to obtain a high quality OCR result for the text but also to perform a precise automatic recognition of typographical attributes in order to capture the logical structure. For that purpose, we present a method that enables a fine-grained typography classification by training an open source OCR engine both on traditional OCR and typography recognition and show how to map the obtained typography information to the OCR recognized text output. As a test case, we used a German dictionary (Sander's "Wörterbuch der Deutschen Sprache") from the 19th century, which comprises a particularly complex semantic function of typography. Despite the very challenging material, we achieved a character error rate below 0.4% and a typography recognition that assigns the correct label to close to 99% of the words. In contrast to many existing methods, our novel approach works with real historical data and can deal with frequent typography changes even within lines.

  @article{reul2019automatic, abstract = {When converting historical lexica into electronic form the goal is not only to obtain a high quality OCR result for the text but also to perform a precise automatic recognition of typographical attributes in order to capture the logical structure. For that purpose, we present a method that enables a fine-grained typography classification by training an open source OCR engine both on traditional OCR and typography recognition and show how to map the obtained typography information to the OCR recognized text output. As a test case, we used a German dictionary (Sander's "Wörterbuch der Deutschen Sprache") from the 19th century, which comprises a particularly complex semantic function of typography. Despite the very challenging material, we achieved a character error rate below 0.4% and a typography recognition that assigns the correct label to close to 99% of the words. In contrast to many existing methods, our novel approach works with real historical data and can deal with frequent typography changes even within lines.}, author = {Reul, Christian and Göttel, Sebastian and Springmann, Uwe and Wick, Christoph and Würzner, Kay-Michael and Puppe, Frank}, journal = {Proceedings of the 3rd International Conference on Digital Access to Textual Cultural Heritage}, keywords = {myown:selected}, title = {Automatic Semantic Text Tagging on Historical Lexica by Combining OCR and Typography Classification}, year = 2019 }
• 
  Detecting Character References in Literary Novels using a Two Stage Contextual Deep Learning approach Krug, Markus; Kempf, Sebastian; Schmidt, David; Weimer, Lukas; Puppe, Frank (P. Sahle; P. Helling, eds.) (2019). Zenodo.
  • [ BibTeX ]
  • [ URL ]
  @proceedings{krug_markus_2019_4622060, author = {Krug, Markus and Kempf, Sebastian and Schmidt, David and Weimer, Lukas and Puppe, Frank}, editor = {Sahle, Patrick and Helling, Patrick}, keywords = {myown}, month = {mar}, publisher = {Zenodo}, title = {Detecting Character References in Literary Novels using a Two Stage Contextual Deep Learning approach}, year = 2019 }
• 
  State of the Art Optical Character Recognition of 19th Century Fraktur Scripts using Open Source Engines Reul, Christian; Springmann, Uwe; Wick, Christoph; Puppe, Frank in DHd 2019 Digital Humanities: multimedial & multimodal (2019).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  In this paper we evaluate Optical Character Recognition (OCR) of 19th century Fraktur scripts without book-specific training using mixed models, i.e. models trained to recognize a variety of fonts and typesets from previously unseen sources. We describe the training process leading to strong mixed OCR models and compare them to freely available models of the popular open source engines OCRopus and Tesseract as well as the commercial state of the art system ABBYY. For evaluation, we use a varied collection of unseen data from books, journals, and a dictionary from the 19th century. The experiments show that training mixed models with real data is superior to training with synthetic data and that the novel OCR engine Calamari outperforms the other engines considerably, on average reducing ABBYYs character error rate (CER) by over 70%, resulting in an average CER below 1%.

  @article{reul2019state, abstract = {In this paper we evaluate Optical Character Recognition (OCR) of 19th century Fraktur scripts without book-specific training using mixed models, i.e. models trained to recognize a variety of fonts and typesets from previously unseen sources. We describe the training process leading to strong mixed OCR models and compare them to freely available models of the popular open source engines OCRopus and Tesseract as well as the commercial state of the art system ABBYY. For evaluation, we use a varied collection of unseen data from books, journals, and a dictionary from the 19th century. The experiments show that training mixed models with real data is superior to training with synthetic data and that the novel OCR engine Calamari outperforms the other engines considerably, on average reducing ABBYYs character error rate (CER) by over 70%, resulting in an average CER below 1%.}, author = {Reul, Christian and Springmann, Uwe and Wick, Christoph and Puppe, Frank}, journal = {DHd 2019 Digital Humanities: multimedial & multimodal}, keywords = {myown}, title = {State of the Art Optical Character Recognition of 19th Century Fraktur Scripts using Open Source Engines}, year = 2019 }
• 
  Team Xenophilius Lovegood at SemEval-2019 Task 4: Hyperpartisanship Classification using Convolutional Neural Networks Zehe, Albin; Hettinger, Lena; Ernst, Stefan; Hauptmann, Christian; Hotho, Andreas in Proceedings of The 13th International Workshop on Semantic Evaluation (2019).
  • [ BibTeX ]
  @inproceedings{zehe2019xenophilius, author = {Zehe, Albin and Hettinger, Lena and Ernst, Stefan and Hauptmann, Christian and Hotho, Andreas}, booktitle = {Proceedings of The 13th International Workshop on Semantic Evaluation}, keywords = {myown}, publisher = {Association for Computational Linguistics}, title = {Team Xenophilius Lovegood at SemEval-2019 Task 4: Hyperpartisanship Classification using Convolutional Neural Networks}, year = 2019 }
• 
  {Evaluation of state of the art methods for coreference resolution and quotation attribution on German literary novels} Krug, Markus; Schmidt, David; Wehner, Nils; Jannidis, Fotis; Puppe, Frank (2019).
  • [ BibTeX ]
  @unpublished{mkJournalNLE, author = {Krug, Markus and Schmidt, David and Wehner, Nils and Jannidis, Fotis and Puppe, Frank}, journal = {Natural Language Engineering}, keywords = {myown}, note = {Manuscript submitted for publication at Journal of Natural Language Engineering}, publisher = {Cambridge University Press}, title = {{Evaluation of state of the art methods for coreference resolution and quotation attribution on German literary novels}}, year = 2019 }
• 
  {Techniques for High Quality Character Reference Detection on German Historical Novels} Krug, Markus; Schmidt, David; Jannidis, Fotis; Puppe, Frank (2019).
  • [ BibTeX ]
  @unpublished{mkJournalDeGruyter, author = {Krug, Markus and Schmidt, David and Jannidis, Fotis and Puppe, Frank}, journal = {Open Linguistics}, keywords = {myown}, note = {Manuscript submitted for publication at De Gruyter Open Linguistics}, publisher = {De Gruyter Open}, title = {{Techniques for High Quality Character Reference Detection on German Historical Novels}}, year = 2019 }
• 
  Replicating medication trend studies using ad hoc information extraction in a clinical data warehouse. Dietrich, Georg; Krebs, Jonathan; Liman, Leon; Fette, Georg; Ertl, Maximilian; Kaspar, Mathias; Störk, Stefan; Puppe, Frank in BMC Med. Inf. & Decision Making (2019). 19(1) 15:1–15:21.
  • [ BibTeX ]
  • [ URL ]
  @article{journals/midm/DietrichKLFEKSP19, author = {Dietrich, Georg and Krebs, Jonathan and Liman, Leon and Fette, Georg and Ertl, Maximilian and Kaspar, Mathias and Störk, Stefan and Puppe, Frank}, journal = {BMC Med. Inf. & Decision Making}, keywords = {myown}, number = 1, pages = {15:1-15:21}, title = {Replicating medication trend studies using ad hoc information extraction in a clinical data warehouse.}, volume = 19, year = 2019 }
• 
  Implementation of a HL7 CQL engine using the graph database Neo4J Fette, Georg; Kaspar, Mathias; Liman, Leon; Eertl, Maximilian; Krebs, Jonathan; Störk, Stefan; Puppe, Frank (2019).
  • [ BibTeX ]
  @article{fette2019implementation, author = {Fette, Georg and Kaspar, Mathias and Liman, Leon and Eertl, Maximilian and Krebs, Jonathan and Störk, Stefan and Puppe, Frank}, keywords = {myown}, title = {Implementation of a HL7 CQL engine using the graph database Neo4J}, year = 2019 }
• 
  Replicating medication trend studies using ad hoc information extraction in a clinical data warehouse Dietrich, Georg; Krebs, Jonathan; Liman, Leon; Fette, Georg; Ertl, Maximilian; Kaspar, Mathias; Störk, Stefan; Puppe, Frank in BMC Medical Informatics and Decision Making, (B. Central, ed.) (2019). 19(1) 15.
  • [ BibTeX ]
  @article{noauthororeditor, author = {Dietrich, Georg and Krebs, Jonathan and Liman, Leon and Fette, Georg and Ertl, Maximilian and Kaspar, Mathias and Störk, Stefan and Puppe, Frank}, editor = {Central, BioMed}, journal = {BMC Medical Informatics and Decision Making}, keywords = {myown}, number = 1, pages = 15, title = {Replicating medication trend studies using ad hoc information extraction in a clinical data warehouse}, volume = 19, year = 2019 }
• 
  Query Translation between AQL and CQL Fette, Georg; Kaspar, Mathias; Leon, Liman; Ertl, Maximilian; Krebs, Jonathan; Dietrich, Georg; Störk, Stefan; Puppe, Frank (2019).
  • [ BibTeX ]
  @article{fettequery, author = {Fette, Georg and Kaspar, Mathias and Leon, Liman and Ertl, Maximilian and Krebs, Jonathan and Dietrich, Georg and Störk, Stefan and Puppe, Frank}, keywords = {myown}, title = {Query Translation between AQL and CQL}, year = 2019 }
• 
  {Automatic recognition of direct speech without quotation marks. A rule-based approach} Tu, Ngoc Duyen Tanja; Krug, Markus; Brunner, Annelen in Proceedings of DHD (2019).
  • [ BibTeX ]
  @article{tu2019automatic, author = {Tu, Ngoc Duyen Tanja and Krug, Markus and Brunner, Annelen}, journal = {Proceedings of DHD}, keywords = {myown}, title = {{Automatic recognition of direct speech without quotation marks. A rule-based approach}}, year = 2019 }
• 
  OCR4all - An Open-Source Tool Providing a (Semi-)Automatic OCR Workflow for Historical Printings Reul, Christian; Christ, Dennis; Hartelt, Alexander; Balbach, Nico; Wehner, Maximilian; Springmann, Uwe; Wick, Christoph; Grundig, Christine; Büttner, Andreas; Puppe, Frank in ArXiv Preprints (submitted to MDPI - Applied Sciences) (2019).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  Optical Character Recognition (OCR) on historical printings is a challenging task mainly due to the complexity of the layout and the highly variant typography. Nevertheless, in the last few years great progress has been made in the area of historical OCR, resulting in several powerful open-source tools for preprocessing, layout recognition and segmentation, character recognition and post-processing. The drawback of these tools often is their limited applicability by non-technical users like humanist scholars and in particular the combined use of several tools in a workflow. In this paper we present an open-source OCR software called OCR4all, which combines state-of-the-art OCR components and continuous model training into a comprehensive workflow. A comfortable GUI allows error corrections not only in the final output, but already in early stages to minimize error propagations. Further on, extensive configuration capabilities are provided to set the degree of automation of the workflow and to make adaptations to the carefully selected default parameters for specific printings, if necessary. Experiments showed that users with minimal or no experience were able to capture the text of even the earliest printed books with manageable effort and great quality, achieving excellent character error rates (CERs) below 0.5%. The fully automated application on 19th century novels showed that OCR4all can considerably outperform the commercial state-of-the-art tool ABBYY Finereader on moderate layouts if suitably pretrained mixed OCR models are available. The architecture of OCR4all allows the easy integration (or substitution) of newly developed tools for its main components by standardized interfaces like PageXML, thus aiming at continual higher automation for historical printings.

  @article{reul2019ocr4all, abstract = {Optical Character Recognition (OCR) on historical printings is a challenging task mainly due to the complexity of the layout and the highly variant typography. Nevertheless, in the last few years great progress has been made in the area of historical OCR, resulting in several powerful open-source tools for preprocessing, layout recognition and segmentation, character recognition and post-processing. The drawback of these tools often is their limited applicability by non-technical users like humanist scholars and in particular the combined use of several tools in a workflow. In this paper we present an open-source OCR software called OCR4all, which combines state-of-the-art OCR components and continuous model training into a comprehensive workflow. A comfortable GUI allows error corrections not only in the final output, but already in early stages to minimize error propagations. Further on, extensive configuration capabilities are provided to set the degree of automation of the workflow and to make adaptations to the carefully selected default parameters for specific printings, if necessary. Experiments showed that users with minimal or no experience were able to capture the text of even the earliest printed books with manageable effort and great quality, achieving excellent character error rates (CERs) below 0.5%. The fully automated application on 19th century novels showed that OCR4all can considerably outperform the commercial state-of-the-art tool ABBYY Finereader on moderate layouts if suitably pretrained mixed OCR models are available. The architecture of OCR4all allows the easy integration (or substitution) of newly developed tools for its main components by standardized interfaces like PageXML, thus aiming at continual higher automation for historical printings.}, author = {Reul, Christian and Christ, Dennis and Hartelt, Alexander and Balbach, Nico and Wehner, Maximilian and Springmann, Uwe and Wick, Christoph and Grundig, Christine and Büttner, Andreas and Puppe, Frank}, journal = {ArXiv Preprints (submitted to MDPI - Applied Sciences)}, keywords = {myown}, title = {OCR4all - An Open-Source Tool Providing a (Semi-)Automatic OCR Workflow for Historical Printings}, year = 2019 }
• 
  Exploration of Artificial Intelligence Use with ARIES in Multiple Myeloma Research Loda; Krebs; Danhof; Schreder; Solimando; Strifler; Rasche; Kortüm; Kerscher; Knop; et al. in Journal of Clinical Medicine (2019). 8(7) 999.
  • [ BibTeX ]
  • [ URL ]
  @article{Loda_2019, author = {Loda and Krebs and Danhof and Schreder and Solimando and Strifler and Rasche and Kortüm and Kerscher and Knop and et al.}, journal = {Journal of Clinical Medicine}, keywords = {myown}, month = {jul}, number = 7, pages = 999, publisher = {MDPI AG}, title = {Exploration of Artificial Intelligence Use with ARIES in Multiple Myeloma Research}, volume = 8, year = 2019 }
• 
  Implementation of a HL7 CQL engine using the graph database Neo4J Fette, Georg; Kaspar, Mathias; Liman, Leon; Eertl, Maximilian; Krebs, Jonathan; Störk, Stefan; Puppe, Frank (2019).
  • [ BibTeX ]
  @article{fette2019implementation, author = {Fette, Georg and Kaspar, Mathias and Liman, Leon and Eertl, Maximilian and Krebs, Jonathan and Störk, Stefan and Puppe, Frank}, keywords = {myown}, title = {Implementation of a HL7 CQL engine using the graph database Neo4J}, year = 2019 }
• 
  State of the Art Optical Character Recognition of 19th Century Fraktur Scripts using Open Source Engines Reul, Christian; Springmann, Uwe; Wick, Christoph; Puppe, Frank in DHd 2019 Digital Humanities: multimedial & multimodal (2019).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  In this paper we evaluate Optical Character Recognition (OCR) of 19th century Fraktur scripts without book-specific training using mixed models, i.e. models trained to recognize a variety of fonts and typesets from previously unseen sources. We describe the training process leading to strong mixed OCR models and compare them to freely available models of the popular open source engines OCRopus and Tesseract as well as the commercial state of the art system ABBYY. For evaluation, we use a varied collection of unseen data from books, journals, and a dictionary from the 19th century. The experiments show that training mixed models with real data is superior to training with synthetic data and that the novel OCR engine Calamari outperforms the other engines considerably, on average reducing ABBYYs character error rate (CER) by over 70%, resulting in an average CER below 1%.

  @article{reul2019state, abstract = {In this paper we evaluate Optical Character Recognition (OCR) of 19th century Fraktur scripts without book-specific training using mixed models, i.e. models trained to recognize a variety of fonts and typesets from previously unseen sources. We describe the training process leading to strong mixed OCR models and compare them to freely available models of the popular open source engines OCRopus and Tesseract as well as the commercial state of the art system ABBYY. For evaluation, we use a varied collection of unseen data from books, journals, and a dictionary from the 19th century. The experiments show that training mixed models with real data is superior to training with synthetic data and that the novel OCR engine Calamari outperforms the other engines considerably, on average reducing ABBYYs character error rate (CER) by over 70%, resulting in an average CER below 1%.}, author = {Reul, Christian and Springmann, Uwe and Wick, Christoph and Puppe, Frank}, journal = {DHd 2019 Digital Humanities: multimedial & multimodal}, keywords = {myown}, title = {State of the Art Optical Character Recognition of 19th Century Fraktur Scripts using Open Source Engines}, year = 2019 }
• 
  Staff, Symbol and Melody Detection of Medieval Manuscripts Written in Square Notation Using Deep Fully Convolutional Networks Wick, Christoph; Hartelt, Alexander; Puppe, Frank in Applied Sciences (2019). 9(13)
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  Even today, the automatic digitisation of scanned documents in general, but especially the automatic optical music recognition (OMR) of historical manuscripts, still remains an enormous challenge, since both handwritten musical symbols and text have to be identified. This paper focuses on the Medieval so-called square notation developed in the 11th–12th century, which is already composed of staff lines, staves, clefs, accidentals, and neumes that are roughly spoken connected single notes. The aim is to develop an algorithm that captures both the neumes, and in particular its melody, which can be used to reconstruct the original writing. Our pipeline is similar to the standard OMR approach and comprises a novel staff line and symbol detection algorithm based on deep Fully Convolutional Networks (FCN), which perform pixel-based predictions for either staff lines or symbols and their respective types. Then, the staff line detection combines the extracted lines to staves and yields an F 1 -score of over 99% for both detecting lines and complete staves. For the music symbol detection, we choose a novel approach that skips the step to identify neumes and instead directly predicts note components (NCs) and their respective affiliation to a neume. Furthermore, the algorithm detects clefs and accidentals. Our algorithm predicts the symbol sequence of a staff with a diplomatic symbol accuracy rate (dSAR) of about 87%, which includes symbol type and location. If only the NCs without their respective connection to a neume, all clefs and accidentals are of interest, the algorithm reaches an harmonic symbol accuracy rate (hSAR) of approximately 90%. In general, the algorithm recognises a symbol in the manuscript with an F 1 -score of over 96%.

  @article{app9132646, abstract = {Even today, the automatic digitisation of scanned documents in general, but especially the automatic optical music recognition (OMR) of historical manuscripts, still remains an enormous challenge, since both handwritten musical symbols and text have to be identified. This paper focuses on the Medieval so-called square notation developed in the 11th–12th century, which is already composed of staff lines, staves, clefs, accidentals, and neumes that are roughly spoken connected single notes. The aim is to develop an algorithm that captures both the neumes, and in particular its melody, which can be used to reconstruct the original writing. Our pipeline is similar to the standard OMR approach and comprises a novel staff line and symbol detection algorithm based on deep Fully Convolutional Networks (FCN), which perform pixel-based predictions for either staff lines or symbols and their respective types. Then, the staff line detection combines the extracted lines to staves and yields an F 1 -score of over 99% for both detecting lines and complete staves. For the music symbol detection, we choose a novel approach that skips the step to identify neumes and instead directly predicts note components (NCs) and their respective affiliation to a neume. Furthermore, the algorithm detects clefs and accidentals. Our algorithm predicts the symbol sequence of a staff with a diplomatic symbol accuracy rate (dSAR) of about 87%, which includes symbol type and location. If only the NCs without their respective connection to a neume, all clefs and accidentals are of interest, the algorithm reaches an harmonic symbol accuracy rate (hSAR) of approximately 90%. In general, the algorithm recognises a symbol in the manuscript with an F 1 -score of over 96%.}, author = {Wick, Christoph and Hartelt, Alexander and Puppe, Frank}, journal = {Applied Sciences}, keywords = {myown}, number = 13, title = {Staff, Symbol and Melody Detection of Medieval Manuscripts Written in Square Notation Using Deep Fully Convolutional Networks}, volume = 9, year = 2019 }
• 
  Implementation of a HL7 CQL engine using the graph database Neo4J Fette, Georg; Kaspar, Mathias; Liman, Leon; Eertl, Maximilian; Krebs, Jonathan; Störk, Stefan; Puppe, Frank (2019).
  • [ BibTeX ]
  • [ Download ]
  @article{fette2019implementation, author = {Fette, Georg and Kaspar, Mathias and Liman, Leon and Eertl, Maximilian and Krebs, Jonathan and Störk, Stefan and Puppe, Frank}, keywords = {myown}, title = {Implementation of a HL7 CQL engine using the graph database Neo4J}, year = 2019 }
• 
  Identifying Heart Failure Patients by Medical Text Classification. Krebs, Jonathan; Krug, Markus; Fette, Georg; Dietrich, Georg; Ertl, Maximilian; Güder, Gülmisal; Puppe, Frank; Kaspar, Mathias in EFMI-STC, Studies in Health Technology and Informatics, A. S. Shvo, I. Madsen, H.-U. Prokosch, K. Häyrinen, K.-H. Wolf, F. Martín-Sánchez, M. Löbe, T. M. Deserno (eds.) (2019). (Vol. 258) 251–252.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{conf/efmi-stc/KrebsKFDEGPK19, author = {Krebs, Jonathan and Krug, Markus and Fette, Georg and Dietrich, Georg and Ertl, Maximilian and Güder, Gülmisal and Puppe, Frank and Kaspar, Mathias}, booktitle = {EFMI-STC}, crossref = {conf/efmi-stc/2019}, editor = {Shvo, Amnon Shabo and Madsen, Inge and Prokosch, Hans-Ulrich and Häyrinen, Kristiina and Wolf, Klaus-Hendrik and Martín-Sánchez, Fernando and Löbe, Matthias and Deserno, Thomas M.}, keywords = {myown}, pages = {251-252}, publisher = {IOS Press}, series = {Studies in Health Technology and Informatics}, title = {Identifying Heart Failure Patients by Medical Text Classification.}, volume = 258, year = 2019 }
• 
  A Systematic View on Speech Assistants for Service Technicians Baumeister, Joachim; Sehne, Veronika; Wienrich, Carolin in Proceedings of LWDA - Lernen. Wissen. Daten. Analysen 2019 (2019). 195–206.
  • [ BibTeX ]
  @inproceedings{baumeister2019systematic, address = {Humboldt-Universität zu Berlin}, author = {Baumeister, Joachim and Sehne, Veronika and Wienrich, Carolin}, booktitle = {Proceedings of LWDA - Lernen. Wissen. Daten. Analysen 2019}, keywords = {rokt}, month = {oct}, pages = {195-206}, title = {A Systematic View on Speech Assistants for Service Technicians}, year = 2019 }
• 
  Detection of Scenes in Fiction Gius, Evelyn; Jannidis, Fotis; Krug, Markus; Zehe, Albin; Hotho, Andreas; Puppe, Frank; Krebs, Jonathan; Reiter, Nils; Wiedmer, Nathalie; Konle, Leonard in Proceedings of Digital Humanities 2019 (2019).
  • [ BibTeX ]
  @inproceedings{gius2019detection, author = {Gius, Evelyn and Jannidis, Fotis and Krug, Markus and Zehe, Albin and Hotho, Andreas and Puppe, Frank and Krebs, Jonathan and Reiter, Nils and Wiedmer, Nathalie and Konle, Leonard}, booktitle = {Proceedings of Digital Humanities 2019}, keywords = {myown}, title = {Detection of Scenes in Fiction}, year = 2019 }
• 
  Query Translation between AQL and CQL Fette, Georg; Kaspar, Mathias; Leon, Liman; Ertl, Maximilian; Krebs, Jonathan; Dietrich, Georg; Störk, Stefan; Puppe, Frank (2019).
  • [ BibTeX ]
  @article{fettequery, author = {Fette, Georg and Kaspar, Mathias and Leon, Liman and Ertl, Maximilian and Krebs, Jonathan and Dietrich, Georg and Störk, Stefan and Puppe, Frank}, keywords = {myown}, title = {Query Translation between AQL and CQL}, year = 2019 }
• 
  Case-Based Retrieval and Adaptation of Regulatory Documents and their Context Korger, Andreas; Baumeister, Joachim in Proceedings of LWDA - Lernen. Wissen. Daten. Analysen 2019 (2019). 292–303.
  • [ BibTeX ]
  @inproceedings{korger2019casebased, address = {Humboldt-Universität zu Berlin}, author = {Korger, Andreas and Baumeister, Joachim}, booktitle = {Proceedings of LWDA - Lernen. Wissen. Daten. Analysen 2019}, keywords = {myown}, month = {oct}, pages = {292-303}, title = {Case-Based Retrieval and Adaptation of Regulatory Documents and their Context}, year = 2019 }
• 
  Korrektur von fehlerhaften OCR Ergebnissen durch automatisches Alignment mit Texten eines Korpus Bald, Markus; Damiani, Vincenzo; Essler, Holger; Eyeselein, Björn; Reul, Christian; Puppe, Frank in DHd2019: multimedial & multimodal (2019).
  • [ BibTeX ]
  • [ URL ]
  @article{bald2019korrektur, author = {Bald, Markus and Damiani, Vincenzo and Essler, Holger and Eyeselein, Björn and Reul, Christian and Puppe, Frank}, journal = {DHd2019: multimedial & multimodal}, keywords = {myown}, title = {Korrektur von fehlerhaften OCR Ergebnissen durch automatisches Alignment mit Texten eines Korpus}, year = 2019 }
• 
  Query Translation between AQL and CQL Fette, Georg; Kaspar, Mathias; Leon, Liman; Ertl, Maximilian; Krebs, Jonathan; Dietrich, Georg; Störk, Stefan; Puppe, Frank (2019).
  • [ BibTeX ]
  • [ Download ]
  @article{fettequery, author = {Fette, Georg and Kaspar, Mathias and Leon, Liman and Ertl, Maximilian and Krebs, Jonathan and Dietrich, Georg and Störk, Stefan and Puppe, Frank}, keywords = {myown}, title = {Query Translation between AQL and CQL}, year = 2019 }
• 
  Automatic Semantic Text Tagging on Historical Lexica by Combining OCR and Typography Classification Reul, Christian; Göttel, Sebastian; Springmann, Uwe; Wick, Christoph; Würzner, Kay-Michael; Puppe, Frank in Proceedings of the 3rd International Conference on Digital Access to Textual Cultural Heritage (2019).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  When converting historical lexica into electronic form the goal is not only to obtain a high quality OCR result for the text but also to perform a precise automatic recognition of typographical attributes in order to capture the logical structure. For that purpose, we present a method that enables a fine-grained typography classification by training an open source OCR engine both on traditional OCR and typography recognition and show how to map the obtained typography information to the OCR recognized text output. As a test case, we used a German dictionary (Sander's "Wörterbuch der Deutschen Sprache") from the 19th century, which comprises a particularly complex semantic function of typography. Despite the very challenging material, we achieved a character error rate below 0.4% and a typography recognition that assigns the correct label to close to 99% of the words. In contrast to many existing methods, our novel approach works with real historical data and can deal with frequent typography changes even within lines.

  @article{reul2019automatic, abstract = {When converting historical lexica into electronic form the goal is not only to obtain a high quality OCR result for the text but also to perform a precise automatic recognition of typographical attributes in order to capture the logical structure. For that purpose, we present a method that enables a fine-grained typography classification by training an open source OCR engine both on traditional OCR and typography recognition and show how to map the obtained typography information to the OCR recognized text output. As a test case, we used a German dictionary (Sander's "Wörterbuch der Deutschen Sprache") from the 19th century, which comprises a particularly complex semantic function of typography. Despite the very challenging material, we achieved a character error rate below 0.4% and a typography recognition that assigns the correct label to close to 99% of the words. In contrast to many existing methods, our novel approach works with real historical data and can deal with frequent typography changes even within lines.}, author = {Reul, Christian and Göttel, Sebastian and Springmann, Uwe and Wick, Christoph and Würzner, Kay-Michael and Puppe, Frank}, journal = {Proceedings of the 3rd International Conference on Digital Access to Textual Cultural Heritage}, keywords = {myown:selected}, title = {Automatic Semantic Text Tagging on Historical Lexica by Combining OCR and Typography Classification}, year = 2019 }
• 
  Query Translation Between openEHR and i2b2. Georg, Fette; Mathias, Kaspar; Liman, Liman; Georg, Dietrich; Maximilian, Ertl; Jonathan, Krebs; Stefan, Störk; Frank, Puppe (2019).
  • [ BibTeX ]
  • [ Download ]
  @article{georg2019query, author = {Georg, Fette and Mathias, Kaspar and Liman, Liman and Georg, Dietrich and Maximilian, Ertl and Jonathan, Krebs and Stefan, Störk and Frank, Puppe}, keywords = {myown}, title = {Query Translation Between openEHR and i2b2.}, year = 2019 }
• 
  On the Right Track! Analysing and Predicting Navigation Success in Wikipedia Koopmann, Tobias; Dallmann, Alexander; Hettinger, Lena; Niebler, Thomas; Hotho, Andreas in Proceedings of the 30th ACM Conference on Hypertext and Social Media, HT ’19, C. Atzenbeck, J. Rubart, D. E. Millard (eds.) (2019). 143–152.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{koopmann2019right, address = {New York, NY, USA}, author = {Koopmann, Tobias and Dallmann, Alexander and Hettinger, Lena and Niebler, Thomas and Hotho, Andreas}, booktitle = {Proceedings of the 30th ACM Conference on Hypertext and Social Media}, editor = {Atzenbeck, Claus and Rubart, Jessica and Millard, David E.}, keywords = {wikipedia}, pages = {143–152}, publisher = {ACM}, series = {HT '19}, title = {On the Right Track! Analysing and Predicting Navigation Success in Wikipedia}, year = 2019 }
• 
  Extracting and Learning Semantics from Social Web Data Niebler, Thomas PhD thesis, Universit{\"a}t W{\"u}rzburg. (2019).
  • [ BibTeX ]
  • [ Download ]
  @phdthesis{niebler2019extracting, author = {Niebler, Thomas}, keywords = {wikipedia}, school = {Universit{\"a}t W{\"u}rzburg}, title = {Extracting and Learning Semantics from Social Web Data}, type = {doctoralthesis}, year = 2019 }
• 
  Replicating medication trend studies using ad hoc information extraction in a clinical data warehouse. Dietrich, Georg; Krebs, Jonathan; Liman, Leon; Fette, Georg; Ertl, Maximilian; Kaspar, Mathias; Störk, Stefan; Puppe, Frank in BMC Med. Inf. & Decision Making (2019). 19(1) 15:1–15:21.
  • [ BibTeX ]
  • [ URL ]
  @article{journals/midm/DietrichKLFEKSP19, author = {Dietrich, Georg and Krebs, Jonathan and Liman, Leon and Fette, Georg and Ertl, Maximilian and Kaspar, Mathias and Störk, Stefan and Puppe, Frank}, journal = {BMC Med. Inf. & Decision Making}, keywords = {myown}, number = 1, pages = {15:1-15:21}, title = {Replicating medication trend studies using ad hoc information extraction in a clinical data warehouse.}, volume = 19, year = 2019 }
• 
  Experience-based Quality Assessment of Distributed Knowledge Graphs Baumeister, Joachim in WM 2019 - 10te Konferenz Professionelles Wissensmanagement (2019).
  • [ BibTeX ]
  • [ Download ]
  @inproceedings{baumeister2019experiencebased, author = {Baumeister, Joachim}, booktitle = {WM 2019 - 10te Konferenz Professionelles Wissensmanagement}, keywords = {rokt}, title = {Experience-based Quality Assessment of Distributed Knowledge Graphs}, year = 2019 }
• 
  Textual Case-based Adaptation using Semantic Relatedness - A Case Study in the Domain of Security Documents Korger, Andreas; Baumeister, Joachim in WM2019 - 10te Konferenz Professionelles Wissensmanagement (2019).
  • [ BibTeX ]
  @inproceedings{korger2019textual, author = {Korger, Andreas and Baumeister, Joachim}, booktitle = {WM2019 - 10te Konferenz Professionelles Wissensmanagement}, keywords = {rokt}, title = {Textual Case-based Adaptation using Semantic Relatedness - A Case Study in the Domain of Security Documents}, year = 2019 }
• 
  {OMMR}4all — a {Semiautomatic} {Online} {Editor} for {Medieval} {Music} {Notations} Wick, Christoph; Puppe, Frank in 2nd {International} {Workshop} on {Reading} {Music} {Systems}, J. Calvo-Zaragoza, A. Pacha (eds.) (2019). 31–34.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{wick_ommr4all_2019, address = {Delft, The Netherlands}, author = {Wick, Christoph and Puppe, Frank}, booktitle = {2nd {International} {Workshop} on {Reading} {Music} {Systems}}, editor = {Calvo-Zaragoza, Jorge and Pacha, Alexander}, keywords = {myown}, pages = {31–34}, title = {{OMMR}4all — a {Semiautomatic} {Online} {Editor} for {Medieval} {Music} {Notations}}, year = 2019 }

• 
  Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active Learning Reul, Christian; Springmann, Uwe; Wick, Christoph; Puppe, Frank in JLCL: Special Issue on Automatic Text and Layout Recognition (2018). 33(1) 3–24.
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  We combine three methods which significantly improve the OCR accuracy of OCR models trained on early printed books: (1) The pretraining method utilizes the information stored in already existing models trained on a variety of typesets (mixed models) instead of starting the training from scratch. (2) Performing cross fold training on a single set of ground truth data (line images and their transcriptions) with a single OCR engine (OCRopus) produces a committee whose members then vote for the best outcome by also taking the top-N alternatives and their intrinsic confidence values into account. (3) Following the principle of maximal disagreement we select additional training lines which the voters disagree most on, expecting them to offer the highest information gain for a subsequent training (active learning). Evaluations on six early printed books yielded the following results: On average the combination of pretraining and voting improved the character accuracy by 46% when training five folds starting from the same mixed model. This number rose to 53% when using different models for pretraining, underlining the importance of diverse voters. Incorporating active learning improved the obtained results by another 16% on average (evaluated on three of the six books). Overall, the proposed methods lead to an average error rate of 2.5% when training on only 60 lines. Using a substantial ground truth pool of 1,000 lines brought the error rate down even further to less than 1% on average.

  @article{reul2018improving, abstract = {We combine three methods which significantly improve the OCR accuracy of OCR models trained on early printed books: (1) The pretraining method utilizes the information stored in already existing models trained on a variety of typesets (mixed models) instead of starting the training from scratch. (2) Performing cross fold training on a single set of ground truth data (line images and their transcriptions) with a single OCR engine (OCRopus) produces a committee whose members then vote for the best outcome by also taking the top-N alternatives and their intrinsic confidence values into account. (3) Following the principle of maximal disagreement we select additional training lines which the voters disagree most on, expecting them to offer the highest information gain for a subsequent training (active learning). Evaluations on six early printed books yielded the following results: On average the combination of pretraining and voting improved the character accuracy by 46% when training five folds starting from the same mixed model. This number rose to 53% when using different models for pretraining, underlining the importance of diverse voters. Incorporating active learning improved the obtained results by another 16% on average (evaluated on three of the six books). Overall, the proposed methods lead to an average error rate of 2.5% when training on only 60 lines. Using a substantial ground truth pool of 1,000 lines brought the error rate down even further to less than 1% on average.}, author = {Reul, Christian and Springmann, Uwe and Wick, Christoph and Puppe, Frank}, journal = {JLCL: Special Issue on Automatic Text and Layout Recognition}, keywords = {myown:selected}, number = 1, pages = {3-24}, title = {Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active Learning}, volume = 33, year = 2018 }
• 
  Cardiac troponins for the diagnosis of acute myocardial infarction in chronic kidney disease Kraus, Daniel; von Jeinsen, Beatrice; Tzikas, Stergios; Palapies, Lars; Zeller, Tanja; Bickel, Christoph; Fette, Georg; J. Lackner, Karl; Drechsler, Christiane; T. Neumann, Johannes; Baldus, Stephan; Blankenberg, Stefan; Münzel, Thomas; Wanner, Christoph; M. Zeiher, Andreas; Keller, Till in Journal of the American Heart Association (2018). 7(19) e008032.
  • [ BibTeX ]
  • [ URL ]
  @article{kraus2018cardiac, author = {Kraus, Daniel and von Jeinsen, Beatrice and Tzikas, Stergios and Palapies, Lars and Zeller, Tanja and Bickel, Christoph and Fette, Georg and J. Lackner, Karl and Drechsler, Christiane and T. Neumann, Johannes and Baldus, Stephan and Blankenberg, Stefan and Münzel, Thomas and Wanner, Christoph and M. Zeiher, Andreas and Keller, Till}, journal = {Journal of the American Heart Association}, keywords = {myown}, month = {September}, number = 19, pages = {e008032}, title = {Cardiac troponins for the diagnosis of acute myocardial infarction in chronic kidney disease}, volume = 7, year = 2018 }
• 
  Finding Needles in the Haystack: Identifying Patients with Rare Subtype of Multiple Myeloma Supported by a Data Warehouse and Information Extraction. Krebs, Jonathan; Bittrich, Max; Dietrich, Georg; Ertl, Maximilian; Fette, Georg; Kaspar, Mathias; Liman, Leon; Einsele, Hermann; Puppe, Frank; Knop, Stefan in GMDS, Studies in Health Technology and Informatics, U. Hübner, U. Sax, H.-U. Prokosch, B. Breil, H. Binder, A. Zapf, B. Strahwald, T. Beißbarth, N. Grabe, A. Schöler (eds.) (2018). (Vol. 253) 160–164.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{conf/gmds/KrebsBDEFKLEPK18, author = {Krebs, Jonathan and Bittrich, Max and Dietrich, Georg and Ertl, Maximilian and Fette, Georg and Kaspar, Mathias and Liman, Leon and Einsele, Hermann and Puppe, Frank and Knop, Stefan}, booktitle = {GMDS}, crossref = {conf/gmds/2018}, editor = {Hübner, Ursula and Sax, Ulrich and Prokosch, Hans-Ulrich and Breil, Bernhard and Binder, Harald and Zapf, Antonia and Strahwald, Brigitte and Beißbarth, Tim and Grabe, Niels and Schöler, Anke}, keywords = {myown}, pages = {160-164}, publisher = {IOS Press}, series = {Studies in Health Technology and Informatics}, title = {Finding Needles in the Haystack: Identifying Patients with Rare Subtype of Multiple Myeloma Supported by a Data Warehouse and Information Extraction.}, volume = 253, year = 2018 }
• 
  Exporting Data from a Clinical Data Warehouse. Fette, Georg; Kaspar, Mathias; Liman, Leon; Dietrich, Georg; Ertl, Maximilian; Krebs, Jonathan; Störk, Stefan; Puppe, Frank in eHealth, Studies in Health Technology and Informatics, G. Schreier, D. Hayn (eds.) (2018). (Vol. 248) 88–93.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{conf/ehealth2/FetteKLDEKSP18, author = {Fette, Georg and Kaspar, Mathias and Liman, Leon and Dietrich, Georg and Ertl, Maximilian and Krebs, Jonathan and Störk, Stefan and Puppe, Frank}, booktitle = {eHealth}, crossref = {conf/ehealth2/2018}, editor = {Schreier, Günter and Hayn, Dieter}, keywords = {myown}, pages = {88-93}, publisher = {IOS Press}, series = {Studies in Health Technology and Informatics}, title = {Exporting Data from a Clinical Data Warehouse.}, volume = 248, year = 2018 }
• 
  ClaiRE at SemEval-2018 Task 7-Extended Version Hettinger, Lena; Dallmann, Alexander; Zehe, Albin; Niebler, Thomas; Hotho, Andreas in arXiv preprint arXiv:1804.05825 (2018).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  In this paper we describe our post-evaluation results for SemEval-2018 Task 7 on classification of semantic relations in scientific literature for clean (subtask 1.1) and noisy data (subtask 1.2). Due to space limitations we publish an extended version of Hettinger et al. (2018) including further technical details and changes made to the preprocessing step in the post-evaluation phase. Due to these changes Classification of Relations using Embeddings (ClaiRE) achieved an improved F1 score of 75.11% for the first subtask and 81.44% for the second.

  @article{hettinger2018claire, abstract = {In this paper we describe our post-evaluation results for SemEval-2018 Task 7 on classification of semantic relations in scientific literature for clean (subtask 1.1) and noisy data (subtask 1.2). Due to space limitations we publish an extended version of Hettinger et al. (2018) including further technical details and changes made to the preprocessing step in the post-evaluation phase. Due to these changes Classification of Relations using Embeddings (ClaiRE) achieved an improved F1 score of 75.11% for the first subtask and 81.44% for the second.}, author = {Hettinger, Lena and Dallmann, Alexander and Zehe, Albin and Niebler, Thomas and Hotho, Andreas}, journal = {arXiv preprint arXiv:1804.05825}, keywords = {tagging}, note = {This is the extended version for our work: ClaiRE at SemEval-2018 Task 7}, title = {ClaiRE at SemEval-2018 Task 7-Extended Version}, type = {Publication}, year = 2018 }
• 
  Comparison of OCR Accuracy on Early Printed Books using the Open Source Engines Calamari and OCRopus Wick, Christoph; Reul, Christian; Puppe, Frank (2018). (Vol. 33) 79–96.
  • [ BibTeX ]
  @book{wick2018comparison, author = {Wick, Christoph and Reul, Christian and Puppe, Frank}, journal = {JLCL}, keywords = {myown}, number = 1, pages = {79-96}, title = {Comparison of OCR Accuracy on Early Printed Books using the Open Source Engines Calamari and OCRopus}, volume = 33, year = 2018 }
• 
  Analysing Direct Speech in German Novels Jannidis, Fotis; Konle, Leonard; Zehe, Albin; Hotho, Andreas; Krug, Markus in DHd 2018 (2018).
  • [ BibTeX ]
  @inproceedings{jannidis2018analysing, author = {Jannidis, Fotis and Konle, Leonard and Zehe, Albin and Hotho, Andreas and Krug, Markus}, booktitle = {DHd 2018}, keywords = {myown}, title = {Analysing Direct Speech in German Novels}, year = 2018 }
• 
  Comparison of OCR Accuracy on Early Printed Books using the Open Source Engines Calamari and OCRopus Wick, Christoph; Reul, Christian; Puppe, Frank in JLCL: Special Issue on Automatic Text and Layout Recognition (2018). 33(1) 79–96.
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  This paper proposes a combination of a convolutional and an LSTM network to improve the accuracy of OCR on early printed books. While the default approach of line based OCR is to use a single LSTM layer as provided by the well-established OCR software OCRopus (OCRopy), we utilize a CNN- and Pooling-Layer combination in advance of an LSTM layer as implemented by the novel OCR software Calamari. Since historical prints often require book specific models trained on manually labeled ground truth (GT) the goal is to maximize the recognition accuracy of a trained model while keeping the needed manual effort to a minimum. We show, that the deep model significantly outperforms the shallow LSTM network when using both many and only a few training examples, although the deep network has a higher amount of trainable parameters. Hereby, the error rate is reduced by a factor of up to 55%, yielding character error rates (CER) of 1% and below for 1,000 lines of training. To further improve the results, we apply a confidence voting mechanism to achieve CERs below 0.5%. A simple data augmentation scheme and the usage of pretrained models reduces the CER further by up to 62% if only few training data is available. Thus, we require only 100 lines of GT to reach an average CER of 1.2%. The runtime of the deep model for training and prediction of a book behaves very similar to a shallow network when trained on a CPU. However, the usage of a GPU, as supported by Calamari, reduces the prediction time by a factor of at least four and the training time by more than six.

  @article{wick2018comparison, abstract = {This paper proposes a combination of a convolutional and an LSTM network to improve the accuracy of OCR on early printed books. While the default approach of line based OCR is to use a single LSTM layer as provided by the well-established OCR software OCRopus (OCRopy), we utilize a CNN- and Pooling-Layer combination in advance of an LSTM layer as implemented by the novel OCR software Calamari. Since historical prints often require book specific models trained on manually labeled ground truth (GT) the goal is to maximize the recognition accuracy of a trained model while keeping the needed manual effort to a minimum. We show, that the deep model significantly outperforms the shallow LSTM network when using both many and only a few training examples, although the deep network has a higher amount of trainable parameters. Hereby, the error rate is reduced by a factor of up to 55%, yielding character error rates (CER) of 1% and below for 1,000 lines of training. To further improve the results, we apply a confidence voting mechanism to achieve CERs below 0.5%. A simple data augmentation scheme and the usage of pretrained models reduces the CER further by up to 62% if only few training data is available. Thus, we require only 100 lines of GT to reach an average CER of 1.2%. The runtime of the deep model for training and prediction of a book behaves very similar to a shallow network when trained on a CPU. However, the usage of a GPU, as supported by Calamari, reduces the prediction time by a factor of at least four and the training time by more than six.}, author = {Wick, Christoph and Reul, Christian and Puppe, Frank}, journal = {JLCL: Special Issue on Automatic Text and Layout Recognition}, keywords = {myown}, number = 1, pages = {79-96}, title = {Comparison of OCR Accuracy on Early Printed Books using the Open Source Engines Calamari and OCRopus}, volume = 33, year = 2018 }
• 
  Exporting Data from a Clinical Data Warehouse. Fette, Georg; Kaspar, Mathias; Liman, Leon; Dietrich, Georg; Ertl, Maximilian; Krebs, Jonathan; Störk, Stefan; Puppe, Frank in eHealth, Studies in Health Technology and Informatics, G. Schreier, D. Hayn (eds.) (2018). (Vol. 248) 88–93.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{conf/ehealth2/FetteKLDEKSP18, author = {Fette, Georg and Kaspar, Mathias and Liman, Leon and Dietrich, Georg and Ertl, Maximilian and Krebs, Jonathan and Störk, Stefan and Puppe, Frank}, booktitle = {eHealth}, crossref = {conf/ehealth2/2018}, editor = {Schreier, Günter and Hayn, Dieter}, keywords = {myown}, pages = {88-93}, publisher = {IOS Press}, series = {Studies in Health Technology and Informatics}, title = {Exporting Data from a Clinical Data Warehouse.}, volume = 248, year = 2018 }
• 
  Annotation and beyond – Using {ATHEN} Annotation and Text Highlighting Environment Krug, Markus; Tu, Ngoc Duyen Tanja; Weimer, Lukas; Reger, Isabella; Konle, Leonard; Jannidis, Fotis; Puppe, Frank in DHd 2018 (2018).
  • [ BibTeX ]
  @inproceedings{krug2018ATHEN, author = {Krug, Markus and Tu, Ngoc Duyen Tanja and Weimer, Lukas and Reger, Isabella and Konle, Leonard and Jannidis, Fotis and Puppe, Frank}, booktitle = {DHd 2018}, keywords = {myown}, title = {Annotation and beyond – Using {ATHEN} Annotation and Text Highlighting Environment}, year = 2018 }
• 
  {Description of a Corpus of Character References in German Novels - {DROC} [{D}eutsches {RO}man {C}orpus]} Krug, Markus; Puppe, Frank; Reger, Isabella; Weimer, Lukas; Macharowsky, Luisa; Feldhaus, Stephan; Jannidis, Fotis in DARIAH-DE Working Papers (2018).
  • [ BibTeX ]
  @inproceedings{droc, author = {Krug, Markus and Puppe, Frank and Reger, Isabella and Weimer, Lukas and Macharowsky, Luisa and Feldhaus, Stephan and Jannidis, Fotis}, booktitle = {DARIAH-DE Working Papers}, keywords = {myown}, organization = {DARIAH-DE}, title = {{Description of a Corpus of Character References in German Novels - {DROC} [{D}eutsches {RO}man {C}orpus]}}, year = 2018 }
• 
  Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active Learning Reul, Christian; Springmann, Uwe; Wick, Christoph; Puppe, Frank in JLCL (2018). 33(1) 3–24.
  • [ BibTeX ]
  @article{noauthororeditor, author = {Reul, Christian and Springmann, Uwe and Wick, Christoph and Puppe, Frank}, journal = {JLCL}, keywords = {myown}, number = 1, pages = {3-24}, title = {Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active Learning}, volume = 33, year = 2018 }
• 
  Proceedings of the Workshop: ’Knowledge and Experience Management’ (German SIG meeting, FGWM) Baumeister, Joachim; Reuss, Pascal (2018).
  • [ BibTeX ]
  @proceedings{BR:FGWM:18, editor = {Baumeister, Joachim and Reuss, Pascal}, keywords = {myown}, title = {Proceedings of the Workshop: 'Knowledge and Experience Management' (German SIG meeting, FGWM)}, year = 2018 }
• 
  Knowledge-Based Decision Support with Self-Learning Methods Scherer, Klaus Peter; Rieder, Constantin; Germann, Markus; Baumeister, Joachim; Plehn, Stefan in The Twelfth International Conference on Advanced Engineering Computing and Applications in Sciences (ADVCOMP) (2018).
  • [ BibTeX ]
  @inproceedings{scherer2018knowledgebased, author = {Scherer, Klaus Peter and Rieder, Constantin and Germann, Markus and Baumeister, Joachim and Plehn, Stefan}, booktitle = {The Twelfth International Conference on Advanced Engineering Computing and Applications in Sciences (ADVCOMP)}, keywords = {myown}, title = {Knowledge-Based Decision Support with Self-Learning Methods}, year = 2018 }
• 
  Evaluation of Configuration Knowledge in Industrial Manufacturing Baumeister, Joachim in Lernen. Wissen. Daten. Analysen. (LWDA 2018) (2018).
  • [ BibTeX ]
  @conference{baumeister2018evaluation, address = {Mannheim}, author = {Baumeister, Joachim}, booktitle = {Lernen. Wissen. Daten. Analysen. (LWDA 2018)}, keywords = {rokt}, month = {August 22-24}, title = {Evaluation of Configuration Knowledge in Industrial Manufacturing}, year = 2018 }
• 
  Synergies between Knowledge Engineering and Software Engineering Nalepa, Grzegorz J.; Baumeister, Joachim (2018). Springer.
  • [ BibTeX ]
  • [ URL ]
  @book{NalBau2017synergies, author = {Nalepa, Grzegorz J. and Baumeister, Joachim}, keywords = {myown}, publisher = {Springer}, title = {Synergies between Knowledge Engineering and Software Engineering}, year = 2018 }
• 
  Improving OCR Accuracy on Early Printed Books by Utilizing Cross Fold Training and Voting Reul, Christian; Springmann, Uwe; Wick, Christoph; Puppe, Frank in 2018 13th IAPR International Workshop on Document Analysis Systems (2018).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  In this paper we introduce a method that significantly reduces the character error rates for OCR text obtained from OCRopus models trained on early printed books. The method uses a combination of cross fold training and confidence based voting. After allocating the available ground truth in different subsets several training processes are performed, each resulting in a specific OCR model. The OCR text generated by these models then gets voted to determine the final output by taking the recognized characters, their alternatives, and the confidence values assigned to each character into consideration. Experiments on seven early printed books show that the proposed method outperforms the standard approach considerably by reducing the amount of errors by up to 50% and more.

  @article{reul2018voting, abstract = {In this paper we introduce a method that significantly reduces the character error rates for OCR text obtained from OCRopus models trained on early printed books. The method uses a combination of cross fold training and confidence based voting. After allocating the available ground truth in different subsets several training processes are performed, each resulting in a specific OCR model. The OCR text generated by these models then gets voted to determine the final output by taking the recognized characters, their alternatives, and the confidence values assigned to each character into consideration. Experiments on seven early printed books show that the proposed method outperforms the standard approach considerably by reducing the amount of errors by up to 50% and more.}, author = {Reul, Christian and Springmann, Uwe and Wick, Christoph and Puppe, Frank}, journal = {2018 13th IAPR International Workshop on Document Analysis Systems}, keywords = {myown:selected}, title = {Improving OCR Accuracy on Early Printed Books by Utilizing Cross Fold Training and Voting}, year = 2018 }
• 
  Finding Needles in the Haystack: Identifying Patients with Rare Subtype of Multiple Myeloma Supported by a Data Warehouse and Information Extraction. Krebs, Jonathan; Bittrich, Max; Dietrich, Georg; Ertl, Maximilian; Fette, Georg; Kaspar, Mathias; Liman, Leon; Einsele, Hermann; Puppe, Frank; Knop, Stefan in GMDS, Studies in Health Technology and Informatics, U. Hübner, U. Sax, H.-U. Prokosch, B. Breil, H. Binder, A. Zapf, B. Strahwald, T. Beißbarth, N. Grabe, A. Schöler (eds.) (2018). (Vol. 253) 160–164.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{conf/gmds/KrebsBDEFKLEPK18, author = {Krebs, Jonathan and Bittrich, Max and Dietrich, Georg and Ertl, Maximilian and Fette, Georg and Kaspar, Mathias and Liman, Leon and Einsele, Hermann and Puppe, Frank and Knop, Stefan}, booktitle = {GMDS}, crossref = {conf/gmds/2018}, editor = {Hübner, Ursula and Sax, Ulrich and Prokosch, Hans-Ulrich and Breil, Bernhard and Binder, Harald and Zapf, Antonia and Strahwald, Brigitte and Beißbarth, Tim and Grabe, Niels and Schöler, Anke}, keywords = {myown}, pages = {160-164}, publisher = {IOS Press}, series = {Studies in Health Technology and Informatics}, title = {Finding Needles in the Haystack: Identifying Patients with Rare Subtype of Multiple Myeloma Supported by a Data Warehouse and Information Extraction.}, volume = 253, year = 2018 }
• 
  Estimating a bias in ICD encodings for billing purposes Fette, Georg; Krug, Markus; Kaspar, Mathias; Liman, Leon; Dietrich, Georg; Ertl, Maximilian; Krebs, Jonathan; Störk, Stefan; Puppe, Frank in Studies in Health Technology and Informatics, (I. Press, ed.) (2018). 247 141–145.
  • [ BibTeX ]
  • [ URL ]
  @article{fette2018estimating, author = {Fette, Georg and Krug, Markus and Kaspar, Mathias and Liman, Leon and Dietrich, Georg and Ertl, Maximilian and Krebs, Jonathan and Störk, Stefan and Puppe, Frank}, editor = {Press, IOS}, journal = {Studies in Health Technology and Informatics}, keywords = {myown}, month = {April}, pages = {141-145}, title = {Estimating a bias in ICD encodings for billing purposes}, volume = 247, year = 2018 }
• 
  Exporting Data from a Clinical Data Warehouse Fette, Georg; Kaspar, Mathias; Liman, Leon; Dietrich, Georg; Ertl, Maximilian; Krebs, Jonathan; Störk, Stefan; Puppe, Frank in Studies in Health Technology and Informatics, (I. Press, ed.) (2018).
  • [ BibTeX ]
  • [ URL ]
  @article{fette2018exporting, author = {Fette, Georg and Kaspar, Mathias and Liman, Leon and Dietrich, Georg and Ertl, Maximilian and Krebs, Jonathan and Störk, Stefan and Puppe, Frank}, editor = {Press, IOS}, journal = {Studies in Health Technology and Informatics}, keywords = {myown}, month = {may}, title = {Exporting Data from a Clinical Data Warehouse}, year = 2018 }
• 
  ClaiRE at SemEval-2018 Task 7: Classification of Relations using Embeddings Hettinger, Lena; Dallmann, Alexander; Zehe, Albin; Niebler, Thomas; Hotho, Andreas in Proceedings of International Workshop on Semantic Evaluation (SemEval-2018) (2018).
  • [ BibTeX ]
  • [ Download ]
  @inproceedings{hettinger2018semeval, address = {New Orleans, LA, USA}, author = {Hettinger, Lena and Dallmann, Alexander and Zehe, Albin and Niebler, Thomas and Hotho, Andreas}, booktitle = {Proceedings of International Workshop on Semantic Evaluation (SemEval-2018)}, keywords = {semeval}, title = {ClaiRE at SemEval-2018 Task 7: Classification of Relations using Embeddings}, year = 2018 }
• 
  Ad Hoc Information Extraction for Clinical Data Warehouses Dietrich, Georg; Krebs, Jonathan; Fette, Georg; Ertl, Maximilian; Kaspar, Mathias; Störk, Stefan; Puppe, Frank in Methods of Information in Medicine (2018).
  • [ BibTeX ]
  • [ URL ]
  @article{dietrich2018information, author = {Dietrich, Georg and Krebs, Jonathan and Fette, Georg and Ertl, Maximilian and Kaspar, Mathias and Störk, Stefan and Puppe, Frank}, journal = {Methods of Information in Medicine}, keywords = {myown}, title = {Ad Hoc Information Extraction for Clinical Data Warehouses}, year = 2018 }
• 
  Underestimated prevalence of heart failure in hospital inpatients: a comparison of ICD codes and discharge letter information Kaspar, Mathias; Fette, Georg; Güder, Gülmisal; Seidlmayer, Lea; Ertl, Maximilian; Dietrich, Georg; Greger, Helmut; Puppe, Frank; Störk, Stefan in Clinical Research in Cardiology, (S. B. Heidelberg, ed.) (2018). 10.
  • [ BibTeX ]
  • [ URL ]
  @article{kaspar2018underestimated, author = {Kaspar, Mathias and Fette, Georg and Güder, Gülmisal and Seidlmayer, Lea and Ertl, Maximilian and Dietrich, Georg and Greger, Helmut and Puppe, Frank and Störk, Stefan}, editor = {Heidelberg, Springer Berlin}, journal = {Clinical Research in Cardiology}, keywords = {myown}, month = {April}, pages = 10, title = {Underestimated prevalence of heart failure in hospital inpatients: a comparison of ICD codes and discharge letter information}, year = 2018 }
• 
  Finding Needles in the Haystack: Identifying Patients with Rare Subtype of Multiple Myeloma Supported by a Data Warehouse and Information Extraction. Krebs, Jonathan; Bittrich, Max; Dietrich, Georg; Ertl, Maximilian; Fette, Georg; Kaspar, Mathias; Liman, Leon; Einsele, Hermann; Puppe, Frank; Knop, Stefan in GMDS, Studies in Health Technology and Informatics, U. Hübner, U. Sax, H.-U. Prokosch, B. Breil, H. Binder, A. Zapf, B. Strahwald, T. Beißbarth, N. Grabe, A. Schöler (eds.) (2018). (Vol. 253) 160–164.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{conf/gmds/KrebsBDEFKLEPK18, author = {Krebs, Jonathan and Bittrich, Max and Dietrich, Georg and Ertl, Maximilian and Fette, Georg and Kaspar, Mathias and Liman, Leon and Einsele, Hermann and Puppe, Frank and Knop, Stefan}, booktitle = {GMDS}, crossref = {conf/gmds/2018}, editor = {Hübner, Ursula and Sax, Ulrich and Prokosch, Hans-Ulrich and Breil, Bernhard and Binder, Harald and Zapf, Antonia and Strahwald, Brigitte and Beißbarth, Tim and Grabe, Niels and Schöler, Anke}, keywords = {myown}, pages = {160-164}, publisher = {IOS Press}, series = {Studies in Health Technology and Informatics}, title = {Finding Needles in the Haystack: Identifying Patients with Rare Subtype of Multiple Myeloma Supported by a Data Warehouse and Information Extraction.}, volume = 253, year = 2018 }
• 
  Estimating a Bias in ICD Encodings for Billing Purposes. Fette, Georg; Krug, Markus; Kaspar, Mathias; Liman, Leon; Dietrich, Georg; Ertl, Maximilian; Krebs, Jonathan; Störk, Stefan; Puppe, Frank in MIE, Studies in Health Technology and Informatics, A. Ugon, D. Karlsson, G. O. Klein, A. Moen (eds.) (2018). (Vol. 247) 141–145.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{conf/mie/FetteKKLDEKSP18, author = {Fette, Georg and Krug, Markus and Kaspar, Mathias and Liman, Leon and Dietrich, Georg and Ertl, Maximilian and Krebs, Jonathan and Störk, Stefan and Puppe, Frank}, booktitle = {MIE}, crossref = {conf/mie/2018}, editor = {Ugon, Adrien and Karlsson, Daniel and Klein, Gunnar O. and Moen, Anne}, keywords = {myown}, pages = {141-145}, publisher = {IOS Press}, series = {Studies in Health Technology and Informatics}, title = {Estimating a Bias in ICD Encodings for Billing Purposes.}, volume = 247, year = 2018 }
• 
  Ad Hoc Information Extraction for Clinical Data Warehouses Dietrich, Georg; Krebs, Jonathan; Fette, Georg; Ertl, Maximilian; Kaspar, Mathias; Störk, Stefan; Puppe, Frank in Methods of Information in Medicine (2018).
  • [ BibTeX ]
  @article{dietrich2018information, author = {Dietrich, Georg and Krebs, Jonathan and Fette, Georg and Ertl, Maximilian and Kaspar, Mathias and Störk, Stefan and Puppe, Frank}, journal = {Methods of Information in Medicine}, keywords = {myown}, title = {Ad Hoc Information Extraction for Clinical Data Warehouses}, year = 2018 }
• 
  The {SECCO} Ontology for the Retrieval and Generation of Security Concepts Korger, Andreas; Baumeister, Joachim in ICCBR 2018 - 26th International Conference on Case-Based Reasoning (2018).
  • [ BibTeX ]
  @inproceedings{korger2018secco, address = {Stockholm, Sweden}, author = {Korger, Andreas and Baumeister, Joachim}, booktitle = {ICCBR 2018 - 26th International Conference on Case-Based Reasoning}, keywords = {rokt}, month = {July 9-12}, publisher = {Springer}, title = {The {SECCO} Ontology for the Retrieval and Generation of Security Concepts}, year = 2018 }
• 
  Estimating a Bias in ICD Encodings for Billing Purposes. Fette, Georg; Krug, Markus; Kaspar, Mathias; Liman, Leon; Dietrich, Georg; Ertl, Maximilian; Krebs, Jonathan; Störk, Stefan; Puppe, Frank in MIE, Studies in Health Technology and Informatics, A. Ugon, D. Karlsson, G. O. Klein, A. Moen (eds.) (2018). (Vol. 247) 141–145.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{conf/mie/FetteKKLDEKSP18, author = {Fette, Georg and Krug, Markus and Kaspar, Mathias and Liman, Leon and Dietrich, Georg and Ertl, Maximilian and Krebs, Jonathan and Störk, Stefan and Puppe, Frank}, booktitle = {MIE}, crossref = {conf/mie/2018}, editor = {Ugon, Adrien and Karlsson, Daniel and Klein, Gunnar O. and Moen, Anne}, keywords = {myown}, pages = {141-145}, publisher = {IOS Press}, series = {Studies in Health Technology and Informatics}, title = {Estimating a Bias in ICD Encodings for Billing Purposes.}, volume = 247, year = 2018 }

• 
  Semi-automatic Terminology Generation for Information Extraction from German Chest X-ray Reports Krebs, Jonathan; Corovic, Hamo; Dietrich, Georg; Ertl, Max; Fette, Georg; Kaspar, Mathias; Störk, Stefan; Puppe, Frank in Stud Health Inform, Medline und Web of Science (2017).
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  @inproceedings{krebs2017semiautomatic, author = {Krebs, Jonathan and Corovic, Hamo and Dietrich, Georg and Ertl, Max and Fette, Georg and Kaspar, Mathias and Störk, Stefan and Puppe, Frank}, booktitle = {Stud Health Inform, Medline und Web of Science}, keywords = {myown}, title = {Semi-automatic Terminology Generation for Information Extraction from German Chest X-ray Reports}, year = 2017 }
• 
  A customizable importer for the clinical data warehouses PaDaWaN and I2B2 Georg, Fette; Mathias, Kaspar; Georg, Dietrich; Max, Ertl; Jonathan, Krebs; Stefan, Störk; Frank, Puppe in Studies in Health Technology and Informatics (2017).
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  @article{georg2017customizable, author = {Georg, Fette and Mathias, Kaspar and Georg, Dietrich and Max, Ertl and Jonathan, Krebs and Stefan, Störk and Frank, Puppe}, journal = {Studies in Health Technology and Informatics}, keywords = {myown}, title = {A customizable importer for the clinical data warehouses PaDaWaN and I2B2}, year = 2017 }
• 
  {Overcoming Data Sparsity for Relation Detection in German Novels.} Krug, Markus; Reger, Isabella; Jannidis, Fotis; Weimer, Lukas; Madar{\’a}sz, Nathalie; Puppe, Frank in DH (2017).
  • [ BibTeX ]
  @inproceedings{krug2017overcoming, author = {Krug, Markus and Reger, Isabella and Jannidis, Fotis and Weimer, Lukas and Madar{\'a}sz, Nathalie and Puppe, Frank}, booktitle = {DH}, keywords = {myown}, title = {{Overcoming Data Sparsity for Relation Detection in German Novels.}}, year = 2017 }
• 
  Comparison of Methods for Automatic Relation Extraction in German Novels Krug, Markus; Wick, Christoph; Jannidis, Fotis; Reger, Isabella; Weimer, Lukas; Madarasz, Nathalie; Puppe, Frank in Dhd Tagung (2017).
  • [ BibTeX ]
  @article{krugRelationen, author = {Krug, Markus and Wick, Christoph and Jannidis, Fotis and Reger, Isabella and Weimer, Lukas and Madarasz, Nathalie and Puppe, Frank}, journal = {Dhd Tagung}, keywords = {myown}, title = {Comparison of Methods for Automatic Relation Extraction in German Novels}, year = 2017 }
• 
  Extending the Query Language of a Data Warehouse for Patient Recruitment. Dietrich, Georg; Ertl, Maximilian; Fette, Georg; Kaspar, Mathias; Krebs, Jonathan; Mackenrodt, Daniel; Störk, Stefan; Puppe, Frank in GMDS, Studies in Health Technology and Informatics, R. Röhrig, A. Timmer, H. Binder, U. Sax (eds.) (2017). (Vol. 243) 152–156.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{conf/gmds/DietrichEFKKMSP17, author = {Dietrich, Georg and Ertl, Maximilian and Fette, Georg and Kaspar, Mathias and Krebs, Jonathan and Mackenrodt, Daniel and Störk, Stefan and Puppe, Frank}, booktitle = {GMDS}, crossref = {conf/gmds/2017}, editor = {Röhrig, Rainer and Timmer, Antje and Binder, Harald and Sax, Ulrich}, keywords = {myown}, pages = {152-156}, publisher = {IOS Press}, series = {Studies in Health Technology and Informatics}, title = {Extending the Query Language of a Data Warehouse for Patient Recruitment.}, volume = 243, year = 2017 }
• 
  Patient’s and physician’s awareness of kidney disease in coronary heart disease patients – a cross-sectional analysis of the German subset of the EUROASPIRE IV survey Wagner, Martin; Wanner, Christoph; Schich, Martin; Kotseva, Kornelia; Wood, David; Hartmann, Katrin; Fette, Georg; Rücker, Viktoria; Oezkur, Mehmet; Störk, Stefan; Heuschmann, Peter U. in BMC Nephrology (2017).
  • [ BibTeX ]
  • [ URL ]
  @article{wagner2017patients, author = {Wagner, Martin and Wanner, Christoph and Schich, Martin and Kotseva, Kornelia and Wood, David and Hartmann, Katrin and Fette, Georg and Rücker, Viktoria and Oezkur, Mehmet and Störk, Stefan and Heuschmann, Peter U.}, journal = {BMC Nephrology}, keywords = {myown}, title = {Patient’s and physician’s awareness of kidney disease in coronary heart disease patients – a cross-sectional analysis of the German subset of the EUROASPIRE IV survey}, year = 2017 }
• 
  A Customizable Importer for the Clinical Data Warehouses PaDaWaN and I2B2. Fette, Georg; Kaspar, Mathias; Dietrich, Georg; Ertl, Maximilian; Krebs, Jonathan; Störk, Stefan; Puppe, Frank in GMDS, Studies in Health Technology and Informatics, R. Röhrig, A. Timmer, H. Binder, U. Sax (eds.) (2017). (Vol. 243) 90–94.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{conf/gmds/FetteKDEKSP17, author = {Fette, Georg and Kaspar, Mathias and Dietrich, Georg and Ertl, Maximilian and Krebs, Jonathan and Störk, Stefan and Puppe, Frank}, booktitle = {GMDS}, crossref = {conf/gmds/2017}, editor = {Röhrig, Rainer and Timmer, Antje and Binder, Harald and Sax, Ulrich}, keywords = {myown}, pages = {90-94}, publisher = {IOS Press}, series = {Studies in Health Technology and Informatics}, title = {A Customizable Importer for the Clinical Data Warehouses PaDaWaN and I2B2.}, volume = 243, year = 2017 }
• 
  Leaf Identification Using a Deep Convolutional Neural Network Wick, Christoph; Puppe, Frank (2017).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  Convolutional neural networks (CNNs) have become popular especially in computer vision in the last few years because they achieved outstanding performance on different tasks, such as image classifications. We propose a nine-layer CNN for leaf identification using the famous Flavia and Foliage datasets. Usually the supervised learning of deep CNNs requires huge datasets for training. However, the used datasets contain only a few examples per plant species. Therefore, we apply data augmentation and transfer learning to prevent our network from overfitting. The trained CNNs achieve recognition rates above 99% on the Flavia and Foliage datasets, and slightly outperform current methods for leaf classification.

  @misc{wick2017leafidentification, abstract = {Convolutional neural networks (CNNs) have become popular especially in computer vision in the last few years because they achieved outstanding performance on different tasks, such as image classifications. We propose a nine-layer CNN for leaf identification using the famous Flavia and Foliage datasets. Usually the supervised learning of deep CNNs requires huge datasets for training. However, the used datasets contain only a few examples per plant species. Therefore, we apply data augmentation and transfer learning to prevent our network from overfitting. The trained CNNs achieve recognition rates above 99% on the Flavia and Foliage datasets, and slightly outperform current methods for leaf classification.}, author = {Wick, Christoph and Puppe, Frank}, keywords = {myown}, note = {cite arxiv:1712.00967}, title = {Leaf Identification Using a Deep Convolutional Neural Network}, year = 2017 }
• 
  Improving OCR Accuracy on Early Printed Books by utilizing Cross Fold Training and Voting Reul, Christian; Springmann, Uwe; Wick, Christoph; Puppe, Frank (2017).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  In this paper we introduce a method that significantly reduces the character error rates for OCR text obtained from OCRopus models trained on early printed books. The method uses a combination of cross fold training and confidence based voting. After allocating the available ground truth in different subsets several training processes are performed, each resulting in a specific OCR model. The OCR text generated by these models then gets voted to determine the final output by taking the recognized characters, their alternatives, and the confidence values assigned to each character into consideration. Experiments on seven early printed books show that the proposed method outperforms the standard approach considerably by reducing the amount of errors by up to 50% and more.

  @misc{reul2017ocrvoting, abstract = {In this paper we introduce a method that significantly reduces the character error rates for OCR text obtained from OCRopus models trained on early printed books. The method uses a combination of cross fold training and confidence based voting. After allocating the available ground truth in different subsets several training processes are performed, each resulting in a specific OCR model. The OCR text generated by these models then gets voted to determine the final output by taking the recognized characters, their alternatives, and the confidence values assigned to each character into consideration. Experiments on seven early printed books show that the proposed method outperforms the standard approach considerably by reducing the amount of errors by up to 50% and more.}, author = {Reul, Christian and Springmann, Uwe and Wick, Christoph and Puppe, Frank}, keywords = {myown}, note = {cite arxiv:1711.09670}, title = {Improving OCR Accuracy on Early Printed Books by utilizing Cross Fold Training and Voting}, year = 2017 }
• 
  Fully Convolutional Neural Networks for Page Segmentation of Historical Document Images Wick, Christoph; Puppe, Frank (2017).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  We propose a high-performance fully convolutional neural network (FCN) for historical handwritten document segmentation that is designed to process a single page in one step. The advantage of this model beside its speed is its ability to directly learn from raw pixels instead of using preprocessing steps e. g. feature computation or superpixel generation. We show that this network yields better results than existing methods on different public data sets. For evaluation of this model we introduce a novel metric that is independent of ambiguous ground truth called Foreground Pixel Accuracy (FgPA). This pixel based measure only counts foreground pixels in the binarized page, any background pixel is omitted. The major advantage of this metric is, that it enables researchers to compare different segmentation methods on their ability to successfully segment text or pictures and not on their ability to learn and possibly overfit the peculiarities of an ambiguous hand-made ground truth segmentation.

  @misc{wick2017fcnhistdoc, abstract = {We propose a high-performance fully convolutional neural network (FCN) for historical handwritten document segmentation that is designed to process a single page in one step. The advantage of this model beside its speed is its ability to directly learn from raw pixels instead of using preprocessing steps e. g. feature computation or superpixel generation. We show that this network yields better results than existing methods on different public data sets. For evaluation of this model we introduce a novel metric that is independent of ambiguous ground truth called Foreground Pixel Accuracy (FgPA). This pixel based measure only counts foreground pixels in the binarized page, any background pixel is omitted. The major advantage of this metric is, that it enables researchers to compare different segmentation methods on their ability to successfully segment text or pictures and not on their ability to learn and possibly overfit the peculiarities of an ambiguous hand-made ground truth segmentation.}, author = {Wick, Christoph and Puppe, Frank}, keywords = {myown}, note = {cite arxiv:1711.07695Comment: 6 pages, 8 figures, conference}, title = {Fully Convolutional Neural Networks for Page Segmentation of Historical Document Images}, year = 2017 }
• 
  Patients not consenting in registry participation- another black box in acute heart failure registries. Results from AHF Registry Feldmann, C; Mathias, Kaspar; Mittenzwei, K; Mohrbach, Carline; Ertl, Max; Fette, Georg; Puppe, Frank; Ertl, Georg; Angermann, Chritine; Stoerk, Stefan (2017).
  • [ BibTeX ]
  • [ URL ]
  @conference{feldmann2017patients, author = {Feldmann, C and Mathias, Kaspar and Mittenzwei, K and Mohrbach, Carline and Ertl, Max and Fette, Georg and Puppe, Frank and Ertl, Georg and Angermann, Chritine and Stoerk, Stefan}, keywords = {myown}, title = {Patients not consenting in registry participation- another black box in acute heart failure registries. Results from AHF Registry}, year = 2017 }
• 
  Transfer Learning for OCRopus Model Training on Early Printed Books Reul, Christian; Wick, Christoph; Springmann, Uwe; Puppe, Frank (2017).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  A method is presented that significantly reduces the character error rates for OCR text obtained from OCRopus models trained on early printed books when only small amounts of diplomatic transcriptions are available. This is achieved by building from already existing models during training instead of starting from scratch. To overcome the discrepancies between the set of characters of the pretrained model and the additional ground truth the OCRopus code is adapted to allow for alphabet expansion or reduction. The character set is now capable of flexibly adding and deleting characters from the pretrained alphabet when an existing model is loaded. For our experiments we use a self-trained mixed model on early Latin prints and the two standard OCRopus models on modern English and German Fraktur texts. The evaluation on seven early printed books showed that training from the Latin mixed model reduces the average amount of errors by 43% and 26%, respectively compared to training from scratch with 60 and 150 lines of ground truth, respectively. Furthermore, it is shown that even building from mixed models trained on data unrelated to the newly added training and test data can lead to significantly improved recognition results.

  @misc{reul2017transfer, abstract = {A method is presented that significantly reduces the character error rates for OCR text obtained from OCRopus models trained on early printed books when only small amounts of diplomatic transcriptions are available. This is achieved by building from already existing models during training instead of starting from scratch. To overcome the discrepancies between the set of characters of the pretrained model and the additional ground truth the OCRopus code is adapted to allow for alphabet expansion or reduction. The character set is now capable of flexibly adding and deleting characters from the pretrained alphabet when an existing model is loaded. For our experiments we use a self-trained mixed model on early Latin prints and the two standard OCRopus models on modern English and German Fraktur texts. The evaluation on seven early printed books showed that training from the Latin mixed model reduces the average amount of errors by 43% and 26%, respectively compared to training from scratch with 60 and 150 lines of ground truth, respectively. Furthermore, it is shown that even building from mixed models trained on data unrelated to the newly added training and test data can lead to significantly improved recognition results.}, author = {Reul, Christian and Wick, Christoph and Springmann, Uwe and Puppe, Frank}, keywords = {myown}, note = {cite arxiv:1712.05586}, title = {Transfer Learning for OCRopus Model Training on Early Printed Books}, year = 2017 }
• 
  Transfer Learning for OCRopus Model Training on Early Printed Books Reul, Christian; Wick, Christoph; Springmann, Uwe; Puppe, Frank in 027.7 Journal for Library Culture (2017).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  A method is presented that significantly reduces the character error rates for OCR text obtained from OCRopus models trained on early printed books when only small amounts of diplomatic transcriptions are available. This is achieved by building from already existing models during training instead of starting from scratch. To overcome the discrepancies between the set of characters of the pretrained model and the additional ground truth the OCRopus code is adapted to allow for alphabet expansion or reduction. The character set is now capable of flexibly adding and deleting characters from the pretrained alphabet when an existing model is loaded. For our experiments we use a self-trained mixed model on early Latin prints and the two standard OCRopus models on modern English and German Fraktur texts. The evaluation on seven early printed books showed that training from the Latin mixed model reduces the average amount of errors by 43% and 26%, compared to training from scratch with 60 and 150 lines of ground truth, respectively. Furthermore, it is shown that even building from mixed models trained on standard data unrelated to the newly added training and test data can lead to significantly improved recognition results.

  @article{reul2017transfer, abstract = {A method is presented that significantly reduces the character error rates for OCR text obtained from OCRopus models trained on early printed books when only small amounts of diplomatic transcriptions are available. This is achieved by building from already existing models during training instead of starting from scratch. To overcome the discrepancies between the set of characters of the pretrained model and the additional ground truth the OCRopus code is adapted to allow for alphabet expansion or reduction. The character set is now capable of flexibly adding and deleting characters from the pretrained alphabet when an existing model is loaded. For our experiments we use a self-trained mixed model on early Latin prints and the two standard OCRopus models on modern English and German Fraktur texts. The evaluation on seven early printed books showed that training from the Latin mixed model reduces the average amount of errors by 43% and 26%, compared to training from scratch with 60 and 150 lines of ground truth, respectively. Furthermore, it is shown that even building from mixed models trained on standard data unrelated to the newly added training and test data can lead to significantly improved recognition results.}, author = {Reul, Christian and Wick, Christoph and Springmann, Uwe and Puppe, Frank}, journal = {027.7 Journal for Library Culture}, keywords = {myown}, title = {Transfer Learning for OCRopus Model Training on Early Printed Books}, year = 2017 }
• 
  Learning Semantic Relatedness from Human Feedback Using Relative Relatedness Learning Niebler, Thomas; Becker, Martin; Pölitz, Christian; Hotho, Andreas in Proceedings of the ISWC 2017, N. Nikitina, D. Song, A. Fokoue, P. Haase (eds.) (2017).
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  @inproceedings{niebler2017learning_3, author = {Niebler, Thomas and Becker, Martin and Pölitz, Christian and Hotho, Andreas}, booktitle = {Proceedings of the ISWC 2017}, editor = {Nikitina, Nadeschda and Song, Dezhao and Fokoue, Achille and Haase, Peter}, keywords = {solvatio}, title = {Learning Semantic Relatedness from Human Feedback Using Relative Relatedness Learning}, year = 2017 }
• 
  Extending the Query Language of a Data Warehouse for Patient Recruitment Dietrich, Georg; Ertl, Max; Fette, Georg; Kaspar, Mathias; Krebs, Jonathan; Mackenrodt, Daniel; Stefan, Störk; Frank, Puppe in Stud Health Inform, Medline und Web of Science (2017).
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  @inproceedings{dietrich2017extending, author = {Dietrich, Georg and Ertl, Max and Fette, Georg and Kaspar, Mathias and Krebs, Jonathan and Mackenrodt, Daniel and Stefan, Störk and Frank, Puppe}, booktitle = {Stud Health Inform, Medline und Web of Science}, keywords = {myown}, title = {Extending the Query Language of a Data Warehouse for Patient Recruitment}, year = 2017 }
• 
  LAREX – A semi-automatic open-source Tool for Layout Analysis and Region Extraction on Early Printed Books Reul, Christian; Springmann, Uwe; Puppe, Frank in Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage (2017).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  A semi-automatic open-source tool for layout analysis on early printed books is presented. LAREX uses a rule based connected components approach which is very fast, easily comprehensible for the user and allows an intuitive manual correction if necessary. The PageXML format is used to support integration into existing OCR workflows. Evaluations showed that LAREX provides an efficient and flexible way to segment pages of early printed books.

  @article{reul2017larex, abstract = {A semi-automatic open-source tool for layout analysis on early printed books is presented. LAREX uses a rule based connected components approach which is very fast, easily comprehensible for the user and allows an intuitive manual correction if necessary. The PageXML format is used to support integration into existing OCR workflows. Evaluations showed that LAREX provides an efficient and flexible way to segment pages of early printed books.}, author = {Reul, Christian and Springmann, Uwe and Puppe, Frank}, journal = {Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage}, keywords = {segmentation}, publisher = {ACM}, title = {LAREX – A semi-automatic open-source Tool for Layout Analysis and Region Extraction on Early Printed Books}, year = 2017 }
• 
  Case Study of a highly automated Layout Analysis and OCR of an incunabulum: ‘Der Heiligen Leben’ (1488) Reul, Christian; Dittrich, Marco; Gruner, Martin in Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage (2017).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  This paper provides the first thorough documentation of a high quality digitization process applied to an early printed book from the incunabulum period (1450-1500). The entire OCR related workflow including preprocessing, layout analysis and text recognition is illustrated in detail using the example of ‘Der Heiligen Leben’, printed in Nuremberg in 1488. For each step the required time expenditure was recorded. The character recognition yielded excellent results both on character (97.57%) and word (92.19%) level. Furthermore, a comparison of a highly automated (LAREX) and a manual (Aletheia) method for layout analysis was performed. By considerably automating the segmentation the required human effort was reduced significantly from over 100 hours to less than six hours, resulting in only a slight drop in OCR accuracy. Realistic estimates for the human effort necessary for full text extraction from incunabula can be derived from this study. The printed pages of the complete work together with the OCR result is available online 1 ready to be inspected and downloaded.

  @article{reul2017study, abstract = {This paper provides the first thorough documentation of a high quality digitization process applied to an early printed book from the incunabulum period (1450-1500). The entire OCR related workflow including preprocessing, layout analysis and text recognition is illustrated in detail using the example of ‘Der Heiligen Leben’, printed in Nuremberg in 1488. For each step the required time expenditure was recorded. The character recognition yielded excellent results both on character (97.57%) and word (92.19%) level. Furthermore, a comparison of a highly automated (LAREX) and a manual (Aletheia) method for layout analysis was performed. By considerably automating the segmentation the required human effort was reduced significantly from over 100 hours to less than six hours, resulting in only a slight drop in OCR accuracy. Realistic estimates for the human effort necessary for full text extraction from incunabula can be derived from this study. The printed pages of the complete work together with the OCR result is available online 1 ready to be inspected and downloaded.}, author = {Reul, Christian and Dittrich, Marco and Gruner, Martin}, journal = {Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage}, keywords = {segmentation}, publisher = {ACM}, title = {Case Study of a highly automated Layout Analysis and OCR of an incunabulum: ‘Der Heiligen Leben’ (1488)}, year = 2017 }
• 
  SP308 INTRA-INDIVIDUAL CHANGES IN HIGH-SENSITIVE TROPONIN I AND T LEVELS IMPROVE DIAGNOSTIC PERFORMANCE FOR ACUTE MYOCARDIAL INFARCTION IN PATIENTS WITH CHRONIC KIDNEY DISEASE Kraus, Daniel; von Jeinsen, Beatrice; Tzikas, Stergios; Palapies, Lars; Zeller, Tanja; Bickel, Christoph; Fette, Georg; Lackner, Karl; Drechsler, Christiane; Neumann, Johannes; others in Nephrology Dialysis Transplantation (2017). 32(suppl\_3) iii211-iii211.
  • [ BibTeX ]
  • [ URL ]
  @article{kraus2017sp308, author = {Kraus, Daniel and von Jeinsen, Beatrice and Tzikas, Stergios and Palapies, Lars and Zeller, Tanja and Bickel, Christoph and Fette, Georg and Lackner, Karl and Drechsler, Christiane and Neumann, Johannes and others}, journal = {Nephrology Dialysis Transplantation}, keywords = {myown}, number = {suppl\_3}, pages = {iii211–iii211}, publisher = {Oxford University Press}, title = {SP308 INTRA-INDIVIDUAL CHANGES IN HIGH-SENSITIVE TROPONIN I AND T LEVELS IMPROVE DIAGNOSTIC PERFORMANCE FOR ACUTE MYOCARDIAL INFARCTION IN PATIENTS WITH CHRONIC KIDNEY DISEASE}, volume = 32, year = 2017 }
• 
  Learning Semantic Relatedness From Human Feedback Using Metric Learning Niebler, Thomas; Becker, Martin; Pölitz, Christian; Hotho, Andreas in arXiv preprint arXiv:1705.07425 (2017).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  Assessing the degree of semantic relatedness between words is an important task with a variety of semantic applications, such as ontology learning for the Semantic Web, semantic search or query expansion. To accomplish this in an automated fashion, many relatedness measures have been proposed. However, most of these metrics only encode information contained in the underlying corpus and thus do not directly model human intuition. To solve this, we propose to utilize a metric learning approach to improve existing semantic relatedness measures by learning from additional information, such as explicit human feedback. For this, we argue to use word embeddings instead of traditional high-dimensional vector representations in order to leverage their semantic density and to reduce computational cost. We rigorously test our approach on several domains including tagging data as well as publicly available embeddings based on Wikipedia texts and navigation. Human feedback about semantic relatedness for learning and evaluation is extracted from publicly available datasets such as MEN or WS-353. We find that our method can significantly improve semantic relatedness measures by learning from additional information, such as explicit human feedback. For tagging data, we are the first to generate and study embeddings. Our results are of special interest for ontology and recommendation engineers, but also for any other researchers and practitioners of Semantic Web techniques.

  @article{niebler2017learning, abstract = {Assessing the degree of semantic relatedness between words is an important task with a variety of semantic applications, such as ontology learning for the Semantic Web, semantic search or query expansion. To accomplish this in an automated fashion, many relatedness measures have been proposed. However, most of these metrics only encode information contained in the underlying corpus and thus do not directly model human intuition. To solve this, we propose to utilize a metric learning approach to improve existing semantic relatedness measures by learning from additional information, such as explicit human feedback. For this, we argue to use word embeddings instead of traditional high-dimensional vector representations in order to leverage their semantic density and to reduce computational cost. We rigorously test our approach on several domains including tagging data as well as publicly available embeddings based on Wikipedia texts and navigation. Human feedback about semantic relatedness for learning and evaluation is extracted from publicly available datasets such as MEN or WS-353. We find that our method can significantly improve semantic relatedness measures by learning from additional information, such as explicit human feedback. For tagging data, we are the first to generate and study embeddings. Our results are of special interest for ontology and recommendation engineers, but also for any other researchers and practitioners of Semantic Web techniques.}, author = {Niebler, Thomas and Becker, Martin and Pölitz, Christian and Hotho, Andreas}, journal = {arXiv preprint arXiv:1705.07425}, keywords = {semantic}, note = {cite arxiv: 1705.07425}, title = {Learning Semantic Relatedness From Human Feedback Using Metric Learning}, type = {Publication}, year = 2017 }
• 
  Constructing Technical Knowledge Organizations from Document Structures Furth, Sebastian; Baumeister, Joachim in Natural Language Processing and Information Systems: 22nd International Conference on Applications of Natural Language to Information Systems, NLDB 2017, Li{\`e}ge, Belgium, June 21-23, 2017, Proceedings, F. Frasincar, A. Ittoo, L. M. Nguyen, E. M{\’e}tais (eds.) (2017). 210–213.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{Furth2017, address = {Cham}, author = {Furth, Sebastian and Baumeister, Joachim}, booktitle = {Natural Language Processing and Information Systems: 22nd International Conference on Applications of Natural Language to Information Systems, NLDB 2017, Li{\`e}ge, Belgium, June 21-23, 2017, Proceedings}, editor = {Frasincar, Flavius and Ittoo, Ashwin and Nguyen, Le Minh and M{\'e}tais, Elisabeth}, keywords = {myown}, pages = {210–213}, publisher = {Springer International Publishing}, title = {Constructing Technical Knowledge Organizations from Document Structures}, year = 2017 }
• 
  TEKNO: Preparing Legacy Technical Documents for Semantic Information Systems Furth, Sebastian; Schirm, Maximilian; Belli, Volker; Baumeister, Joachim in Natural Language Processing and Information Systems: 22nd International Conference on Applications of Natural Language to Information Systems, NLDB 2017, Li{\`e}ge, Belgium, June 21-23, 2017, Proceedings, F. Frasincar, A. Ittoo, L. M. Nguyen, E. M{\’e}tais (eds.) (2017). 429–434.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{Furth2017, address = {Cham}, author = {Furth, Sebastian and Schirm, Maximilian and Belli, Volker and Baumeister, Joachim}, booktitle = {Natural Language Processing and Information Systems: 22nd International Conference on Applications of Natural Language to Information Systems, NLDB 2017, Li{\`e}ge, Belgium, June 21-23, 2017, Proceedings}, editor = {Frasincar, Flavius and Ittoo, Ashwin and Nguyen, Le Minh and M{\'e}tais, Elisabeth}, keywords = {myown}, pages = {429–434}, publisher = {Springer International Publishing}, title = {TEKNO: Preparing Legacy Technical Documents for Semantic Information Systems}, year = 2017 }
• 
  Knowledge Acquisition by Selflearning Methods with Structured Clinical Data Scherer, Klaus Peter; Knöll, Daniel; Baumeister, Joachim; Furth, Sebastian in IJAS: International Conference on Arts and Sciences (2017).
  • [ BibTeX ]
  @inproceedings{scherer2017knowledge, address = {Montreal}, author = {Scherer, Klaus Peter and Knöll, Daniel and Baumeister, Joachim and Furth, Sebastian}, booktitle = {IJAS: International Conference on Arts and Sciences}, keywords = {myown}, title = {Knowledge Acquisition by Selflearning Methods with Structured Clinical Data}, year = 2017 }
• 
  Learning Word Embeddings from Tagging Data: A methodological comparison Niebler, Thomas; Hahn, Luzian; Hotho, Andreas in Proceedings of the LWDA (2017).
  • [ BibTeX ]
  • [ Download ]
  @inproceedings{niebler2017learning_2, author = {Niebler, Thomas and Hahn, Luzian and Hotho, Andreas}, booktitle = {Proceedings of the LWDA}, keywords = {word2vec}, title = {Learning Word Embeddings from Tagging Data: A methodological comparison}, year = 2017 }
• 
  Vergleich und Integration der Data Warehouse Architekturen PaDaWaN und i2b2 Liman, Leon (2017).
  • [ BibTeX ]
  • [ Download ]
  @mastersthesis{liman2017dwPai2, author = {Liman, Leon}, keywords = {myown}, title = {Vergleich und Integration der Data Warehouse Architekturen PaDaWaN und i2b2}, year = 2017 }
• 
  Playing Music in Just Intonation - A Dynamically Adapting Tuning Scheme Stange, Karolin; Wick, Christoph; Hinrichsen, Haye (2017).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  We introduce a dynamically adapting tuning scheme for microtonal tuning of musical instruments, allowing the performer to play music in just intonation in any key. Unlike previous methods, which are based on a procedural analysis of the chordal structure, the suggested tuning scheme continually solves a system of linear equations without making explicit decisions. In complex situations, where not all intervals of a chord can be tuned according to just frequency ratios, the method automatically yields a tempered compromise. We outline the implementation of the algorithm in an open-source software project that we have provided in order to demonstrate the feasibility of the tuning method.

  @misc{stange2017playing, abstract = {We introduce a dynamically adapting tuning scheme for microtonal tuning of musical instruments, allowing the performer to play music in just intonation in any key. Unlike previous methods, which are based on a procedural analysis of the chordal structure, the suggested tuning scheme continually solves a system of linear equations without making explicit decisions. In complex situations, where not all intervals of a chord can be tuned according to just frequency ratios, the method automatically yields a tempered compromise. We outline the implementation of the algorithm in an open-source software project that we have provided in order to demonstrate the feasibility of the tuning method.}, author = {Stange, Karolin and Wick, Christoph and Hinrichsen, Haye}, keywords = {myown}, note = {cite arxiv:1706.04338Comment: 21 pages, 4 figures}, title = {Playing Music in Just Intonation - A Dynamically Adapting Tuning Scheme}, year = 2017 }
• 
  Semi-Automatic Terminology Generation for Information Extraction from German Chest X-Ray Reports. Krebs, Jonathan; Corovic, Hamo; Dietrich, Georg; Ertl, Max; Fette, Georg; Kaspar, Mathias; Krug, Markus; Störk, Stefan; Puppe, Frank in GMDS, Studies in Health Technology and Informatics, R. Röhrig, A. Timmer, H. Binder, U. Sax (eds.) (2017). (Vol. 243) 80–84.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{conf/gmds/KrebsCDEFKKSP17, author = {Krebs, Jonathan and Corovic, Hamo and Dietrich, Georg and Ertl, Max and Fette, Georg and Kaspar, Mathias and Krug, Markus and Störk, Stefan and Puppe, Frank}, booktitle = {GMDS}, crossref = {conf/gmds/2017}, editor = {Röhrig, Rainer and Timmer, Antje and Binder, Harald and Sax, Ulrich}, keywords = {myown}, pages = {80-84}, publisher = {IOS Press}, series = {Studies in Health Technology and Informatics}, title = {Semi-Automatic Terminology Generation for Information Extraction from German Chest X-Ray Reports.}, volume = 243, year = 2017 }

• 
  Data Linkage from Clinical to Study Databases via an R Data Warehouse User Interface Kaspar, M; Ertl, M; Fette, G; Dietrich, G; Toepfer, M; Angermann, C; St{\"o}rk, S; Puppe, F; others in Methods of Information in Medicine (2016). 55(4) 381–386.
  • [ BibTeX ]
  • [ URL ]
  @article{kaspar2016data, author = {Kaspar, M and Ertl, M and Fette, G and Dietrich, G and Toepfer, M and Angermann, C and St{\"o}rk, S and Puppe, F and others}, journal = {Methods of Information in Medicine}, keywords = {myown}, number = 4, pages = {381–386}, publisher = {Schattauer Publishers}, title = {Data Linkage from Clinical to Study Databases via an R Data Warehouse User Interface}, volume = 55, year = 2016 }
• 
  Requirements of Affective Information Systems in the Industrial Domain Baumeister, Joachim in Proceedings of Affective Computing and Context Awareness in Ambient Intelligence, Nalepa (ed.) (2016).
  • [ BibTeX ]
  @inproceedings{baumeister2016requirements, author = {Baumeister, Joachim}, booktitle = {Proceedings of Affective Computing and Context Awareness in Ambient Intelligence}, editor = {Nalepa}, keywords = {rokt}, title = {Requirements of Affective Information Systems in the Industrial Domain}, year = 2016 }
• 
  UIMA Ruta: Rapid development of rule-based information extraction applications. Kluegl, Peter; Toepfer, Martin; Beck, Philip-Daniel; Fette, Georg; Puppe, Frank in Natural Language Engineering (2016). 22(1) 1–40.
  • [ BibTeX ]
  • [ URL ]
  @article{journals/nle/KlueglTBFP16, author = {Kluegl, Peter and Toepfer, Martin and Beck, Philip-Daniel and Fette, Georg and Puppe, Frank}, journal = {Natural Language Engineering}, keywords = {myown}, number = 1, pages = {1-40}, title = {UIMA Ruta: Rapid development of rule-based information extraction applications.}, volume = 22, year = 2016 }
• 
  CAPLAN: An Accessible, Flexible and Scalable Semantification Architecture Furth, Sebastian; Belli, Volker; Legler, Alexander; Striffler, Albrecht; Baumeister, Joachim in Proceedings of the Conference "Lernen, Wissen, Daten, Analysen" (2016).
  • [ BibTeX ]
  @inproceedings{furth2016caplan, author = {Furth, Sebastian and Belli, Volker and Legler, Alexander and Striffler, Albrecht and Baumeister, Joachim}, booktitle = {Proceedings of the Conference "Lernen, Wissen, Daten, Analysen"}, keywords = {nlp}, title = {CAPLAN: An Accessible, Flexible and Scalable Semantification Architecture}, year = 2016 }
• 
  An improved data workflow for a medical data warehouse Fette, Georg; Ertl, Maximilian; Dietrich, Georg; Krebs, Jonathan; Toepfer, Martin; Störk, Stefan; Kaspar, Mathias; Puppe, Frank in European Journal of Epidemiology; Health—exploring complexity: an interdisciplinary systems approach HEC2016 (2016). 31, Supplement 1 54.
  • [ Abstract ]
  • [ BibTeX ]
  In recent years clinical data warehouses (CDW) have become more and more popular to support scientific work in the medical domain. Despite the tool support for many subtasks it is still a laborious task to establish a CDW in an existing clinical data environment. We present a workflow which can be taken as a blueprint for newly established CDW projects and the implementation of this blueprint at the University Clinic Würzburg.

  @article{noauthororeditor, abstract = {In recent years clinical data warehouses (CDW) have become more and more popular to support scientific work in the medical domain. Despite the tool support for many subtasks it is still a laborious task to establish a CDW in an existing clinical data environment. We present a workflow which can be taken as a blueprint for newly established CDW projects and the implementation of this blueprint at the University Clinic Würzburg.}, author = {Fette, Georg and Ertl, Maximilian and Dietrich, Georg and Krebs, Jonathan and Toepfer, Martin and Störk, Stefan and Kaspar, Mathias and Puppe, Frank}, journal = {European Journal of Epidemiology; Health—exploring complexity: an interdisciplinary systems approach HEC2016}, keywords = {myown}, month = {August}, pages = 54, title = {An improved data workflow for a medical data warehouse}, volume = {31, Supplement 1}, year = 2016 }
• 
  An improved data workflow for a medical data warehouse Fette, Georg; Ertl, Maximilian; Dietrich, Georg; Krebs, Jonathan; Toepfer, Martin; Störk, Stefan; Kaspar, Mathias; Puppe, Frank in European Journal of Epidemiology; Health—exploring complexity: an interdisciplinary systems approach HEC2016 (2016). 31, Supplement 1 54.
  • [ Abstract ]
  • [ BibTeX ]
  • [ Download ]
  In recent years clinical data warehouses (CDW) have become more and more popular to support scientific work in the medical domain. Despite the tool support for many subtasks it is still a laborious task to establish a CDW in an existing clinical data environment. We present a workflow which can be taken as a blueprint for newly established CDW projects and the implementation of this blueprint at the University Clinic Würzburg.

  @article{noauthororeditor, abstract = {In recent years clinical data warehouses (CDW) have become more and more popular to support scientific work in the medical domain. Despite the tool support for many subtasks it is still a laborious task to establish a CDW in an existing clinical data environment. We present a workflow which can be taken as a blueprint for newly established CDW projects and the implementation of this blueprint at the University Clinic Würzburg.}, author = {Fette, Georg and Ertl, Maximilian and Dietrich, Georg and Krebs, Jonathan and Toepfer, Martin and Störk, Stefan and Kaspar, Mathias and Puppe, Frank}, journal = {European Journal of Epidemiology; Health—exploring complexity: an interdisciplinary systems approach HEC2016}, keywords = {myown}, month = {August}, pages = 54, title = {An improved data workflow for a medical data warehouse}, volume = {31, Supplement 1}, year = 2016 }
• 
  Anonymisierung, Segmentierung und Terminologie-Entwicklung zur Informationsextraktion aus unstrukturierten, telegrammartigen, medizinischen Dokumenten Krebs, Jonathan (2016).
  • [ BibTeX ]
  @mastersthesis{krebs2016anonymisierung, author = {Krebs, Jonathan}, keywords = {myown}, title = {Anonymisierung, Segmentierung und Terminologie-Entwicklung zur Informationsextraktion aus unstrukturierten, telegrammartigen, medizinischen Dokumenten}, year = 2016 }
• 
  Extracting Semantics from Unconstrained Navigation on Wikipedia Niebler, Thomas; Schlör, Daniel; Becker, Martin; Hotho, Andreas in KI -- Künstliche Intelligenz (2016). 30(2) 163–168.
  • [ Abstract ]
  • [ BibTeX ]
  • [ Download ]
  Semantic relatedness between words has been successfully extracted from navigation on Wikipedia pages. However, the navigational data used in the corresponding works are sparse and expected to be biased since they have been collected in the context of games. In this paper, we raise this limitation and explore if semantic relatedness can also be extracted from unconstrained navigation. To this end, we first highlight structural differences between unconstrained navigation and game data. Then, we adapt a state of the art approach to extract semantic relatedness on Wikipedia paths. We apply this approach to transitions derived from two unconstrained navigation datasets as well as transitions from WikiGame and compare the results based on two common gold standards. We confirm expected structural differences when comparing unconstrained navigation with the paths collected by WikiGame. In line with this result, the mentioned state of the art approach for semantic extraction on navigation data does not yield good results for unconstrained navigation. Yet, we are able to derive a relatedness measure that performs well on both unconstrained navigation data as well as game data. Overall, we show that unconstrained navigation data on Wikipedia is suited for extracting semantics.

  @article{niebler2016extracting, abstract = {Semantic relatedness between words has been successfully extracted from navigation on Wikipedia pages. However, the navigational data used in the corresponding works are sparse and expected to be biased since they have been collected in the context of games. In this paper, we raise this limitation and explore if semantic relatedness can also be extracted from unconstrained navigation. To this end, we first highlight structural differences between unconstrained navigation and game data. Then, we adapt a state of the art approach to extract semantic relatedness on Wikipedia paths. We apply this approach to transitions derived from two unconstrained navigation datasets as well as transitions from WikiGame and compare the results based on two common gold standards. We confirm expected structural differences when comparing unconstrained navigation with the paths collected by WikiGame. In line with this result, the mentioned state of the art approach for semantic extraction on navigation data does not yield good results for unconstrained navigation. Yet, we are able to derive a relatedness measure that performs well on both unconstrained navigation data as well as game data. Overall, we show that unconstrained navigation data on Wikipedia is suited for extracting semantics.}, author = {Niebler, Thomas and Schlör, Daniel and Becker, Martin and Hotho, Andreas}, journal = {KI – Künstliche Intelligenz}, keywords = {wikipedia}, number = 2, pages = {163–168}, publisher = {Springer}, title = {Extracting Semantics from Unconstrained Navigation on Wikipedia}, volume = 30, year = 2016 }
• 
  Extracting Semantics from Random Walks on Wikipedia: Comparing Learning and Counting Methods Dallmann, Alexander; Niebler, Thomas; Lemmerich, Florian; Hotho, Andreas in Proceedings of the 10th International Conference on Web and Social Media, R. West, L. Zia, D. Taraborelli, J. Leskovec (eds.) (2016).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  Semantic relatedness between words has been extracted from a variety of sources.In this ongoing work, we explore and compare several options for determining if semantic relatedness can be extracted from navigation structures in Wikipedia. In that direction, we first investigate the potential of representation learning techniques such as DeepWalk in comparison to previously applied methods based on counting co-occurrences. Since both methods are based on (random) paths in the network, we also study different approaches to generate paths from Wikipedia link structure. For this task, we do not only consider the link structure of Wikipedia, but also actual navigation behavior of users. Finally, we analyze if semantics can also be extracted from smaller subsets of the Wikipedia link network. As a result we find that representation learning techniques mostly outperform the investigated co-occurrence counting methods on the Wikipedia network. However, we find that this is not the case for paths sampled from human navigation behavior.

  @inproceedings{dallmann2016extracting, abstract = {Semantic relatedness between words has been extracted from a variety of sources.In this ongoing work, we explore and compare several options for determining if semantic relatedness can be extracted from navigation structures in Wikipedia. In that direction, we first investigate the potential of representation learning techniques such as DeepWalk in comparison to previously applied methods based on counting co-occurrences. Since both methods are based on (random) paths in the network, we also study different approaches to generate paths from Wikipedia link structure. For this task, we do not only consider the link structure of Wikipedia, but also actual navigation behavior of users. Finally, we analyze if semantics can also be extracted from smaller subsets of the Wikipedia link network. As a result we find that representation learning techniques mostly outperform the investigated co-occurrence counting methods on the Wikipedia network. However, we find that this is not the case for paths sampled from human navigation behavior.}, author = {Dallmann, Alexander and Niebler, Thomas and Lemmerich, Florian and Hotho, Andreas}, booktitle = {Proceedings of the 10th International Conference on Web and Social Media}, editor = {West, Robert and Zia, Leila and Taraborelli, Dario and Leskovec, Jure}, keywords = {word2vec}, publisher = {AAAI}, title = {Extracting Semantics from Random Walks on Wikipedia: Comparing Learning and Counting Methods}, year = 2016 }
• 
  Linked Data City - Visualization of Linked Enterprise Data Baumeister, Joachim; Furth, Sebastian; Roth, Lea; Belli, Volker in Proceedings of the Conference "Lernen, Wissen, Daten, Analysen" (2016).
  • [ BibTeX ]
  @inproceedings{baumeister2016linked, author = {Baumeister, Joachim and Furth, Sebastian and Roth, Lea and Belli, Volker}, booktitle = {Proceedings of the Conference "Lernen, Wissen, Daten, Analysen"}, keywords = {visualization}, title = {Linked Data City - Visualization of Linked Enterprise Data}, year = 2016 }
• 
  Mining Subgroups with Exceptional Transition Behavior Lemmerich, Florian; Becker, Martin; Singer, Philipp; Helic, Denis; Hotho, Andreas; Strohmaier, Markus in KDD ’16: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016).
  • [ BibTeX ]
  @inproceedings{lemmerich2016subtrails, author = {Lemmerich, Florian and Becker, Martin and Singer, Philipp and Helic, Denis and Hotho, Andreas and Strohmaier, Markus}, booktitle = {KDD '16: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining}, keywords = {myown}, organization = {ACM}, title = {Mining Subgroups with Exceptional Transition Behavior}, year = 2016 }
• 
  Deep Learning Wick, Christoph in Informatik-Spektrum (2016). 1–5.
  • [ BibTeX ]
  • [ URL ]
  @article{Wick2016, author = {Wick, Christoph}, journal = {Informatik-Spektrum}, keywords = {myown}, pages = {1–5}, title = {Deep Learning}, year = 2016 }
• 
  {Wissensgenerierung durch Selbstlernverfahren mit strukturierten Katarakt-Daten} Scherer, Klaus Peter; Germann, Markus; Knoell, Daniel; Baumeister, Joachim; Furth, Sebastian in Spektrum für Augenheilkunde (2016). 2 90.
  • [ BibTeX ]
  @article{scherer2016wissensgenerierung, author = {Scherer, Klaus Peter and Germann, Markus and Knoell, Daniel and Baumeister, Joachim and Furth, Sebastian}, journal = {Spektrum für Augenheilkunde}, keywords = {myown}, pages = 90, title = {{Wissensgenerierung durch Selbstlernverfahren mit strukturierten Katarakt-Daten}}, volume = 2, year = 2016 }
• 
  Semantification of Large Corpora of Technical Documentation Furth, Sebastian; Baumeister, Joachim in Enterprise Big Data Engineering, Analytics, and Management, M. Atzmueller, S. Oussena, T. Roth-Berghofer (eds.) (2016).
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{furth2016semantification, author = {Furth, Sebastian and Baumeister, Joachim}, booktitle = {Enterprise Big Data Engineering, Analytics, and Management}, editor = {Atzmueller, Martin and Oussena, Samia and Roth-Berghofer, Thomas}, keywords = {rokt}, publisher = {IGI Global}, title = {Semantification of Large Corpora of Technical Documentation}, type = {Publication}, year = 2016 }
• 
  Attribuierung direkter Reden in deutschen Romanen des 18.-20. Jahrhunderts. Methoden zur Bestimmung des Sprechers und des Angesprochenen Puppe, Frank; Krug, Markus; Jannidis, Fotis; Weimer, Lukas; Macharowsky, Luisa; Reger, Isabella (2016).
  • [ BibTeX ]
  @conference{puppe2016attribuierung, author = {Puppe, Frank and Krug, Markus and Jannidis, Fotis and Weimer, Lukas and Macharowsky, Luisa and Reger, Isabella}, keywords = {myown}, publisher = {DHD 2016}, title = {Attribuierung direkter Reden in deutschen Romanen des 18.-20. Jahrhunderts. Methoden zur Bestimmung des Sprechers und des Angesprochenen}, type = {Publication}, year = 2016 }
• 
  Prevalence of severe mitral regurgitation eligible for edge-to-edge mitral valve repair (MitraClip) Wallenborn, J; St{\"o}rk, S; Herrmann, S; Kukuy, O; Fette, G; Puppe, F; Gorski, A; Hu, K; Voelker, W; Ertl, G; Weidemann, F in Clin Res Cardiol (2016).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  We assessed the prevalence of moderately severe or severe mitral regurgitation (MR) justifying edge-to-edge mitral valve (MV) repair (MitraClip(®)) in patients attending the University Hospital Wuerzburg, a tertiary care centre located in Wuerzburg, Germany.Transcatheter edge-to-edge MV repair of advanced MR is a non-surgical treatment option in inoperable and high-risk patients. It is unknown how many patients are potentially eligible for MitraClip(®) since several anatomical prerequisites of the MV apparatus have to be met for optimal treatment results.Using a novel clinical data warehouse we searched for all patients attached to our Department of Internal Medicine from 01/2008 to 01/2012 with moderately severe or severe MR and aged ≥18 years. The current status of their treatment regime and eligibility for MitraClip(®) was assessed and re-evaluated according to current guidelines and echocardiographic criteria.The search of electronic medical records amongst 43,690 patients employed an innovative validated text extraction method and identified 331 patients with moderately severe or severe MR who had undergone echocardiographic assessment at our institution. Of these, 125 (38 %) received MV surgery and 206 (62 %) medical therapy only. Most patients not undergoing surgery had secondary MR (70 %). After evaluation of medical and echocardiographic data of medically treated patients (n = 206), 81 (39 %) were potential candidates for MitraClip(®) therapy, and 90 (44 %) died during the median follow-up time of 23 months.A large fraction of patients with moderately severe or severe MR but not operated was detected. Medically treated patients had a bad prognosis and about 40 % of them were potential candidates for MitraClip(®) therapy.

  @article{Wallenborn:2016:Clin-Res-Cardiol:26916650, abstract = {We assessed the prevalence of moderately severe or severe mitral regurgitation (MR) justifying edge-to-edge mitral valve (MV) repair (MitraClip(®)) in patients attending the University Hospital Wuerzburg, a tertiary care centre located in Wuerzburg, Germany.Transcatheter edge-to-edge MV repair of advanced MR is a non-surgical treatment option in inoperable and high-risk patients. It is unknown how many patients are potentially eligible for MitraClip(®) since several anatomical prerequisites of the MV apparatus have to be met for optimal treatment results.Using a novel clinical data warehouse we searched for all patients attached to our Department of Internal Medicine from 01/2008 to 01/2012 with moderately severe or severe MR and aged ≥18 years. The current status of their treatment regime and eligibility for MitraClip(®) was assessed and re-evaluated according to current guidelines and echocardiographic criteria.The search of electronic medical records amongst 43,690 patients employed an innovative validated text extraction method and identified 331 patients with moderately severe or severe MR who had undergone echocardiographic assessment at our institution. Of these, 125 (38 %) received MV surgery and 206 (62 %) medical therapy only. Most patients not undergoing surgery had secondary MR (70 %). After evaluation of medical and echocardiographic data of medically treated patients (n = 206), 81 (39 %) were potential candidates for MitraClip(®) therapy, and 90 (44 %) died during the median follow-up time of 23 months.A large fraction of patients with moderately severe or severe MR but not operated was detected. Medically treated patients had a bad prognosis and about 40 % of them were potential candidates for MitraClip(®) therapy.}, author = {Wallenborn, J and St{\"o}rk, S and Herrmann, S and Kukuy, O and Fette, G and Puppe, F and Gorski, A and Hu, K and Voelker, W and Ertl, G and Weidemann, F}, journal = {Clin Res Cardiol}, keywords = {myown}, month = {feb}, title = {Prevalence of severe mitral regurgitation eligible for edge-to-edge mitral valve repair (MitraClip)}, year = 2016 }
• 
  Comparison of Methods for the Identification of Main Characters in German Novels Krug, Markus; Puppe, Frank; Jannidis, Fotis; Reger, Isabella; Weimer, Lukas; Macharowsky, Luisa (2016).
  • [ BibTeX ]
  @conference{krug2016comparison, author = {Krug, Markus and Puppe, Frank and Jannidis, Fotis and Reger, Isabella and Weimer, Lukas and Macharowsky, Luisa}, keywords = {myown}, title = {Comparison of Methods for the Identification of Main Characters in German Novels}, year = 2016 }
• 
  Expectation-driven Text Extraction from Medical Ultrasound Images Reul, Christian; Köberle, Philipp; Üçeyler, Nurcan; Puppe, Frank in Studies in Health Technology and Informatics (2016).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  In this study an expectation-driven approach is proposed to extract data stored as pixel structures in medical ultrasound images. Prior knowledge about certain properties like the position of the text and its background and foreground grayscale values is utilized. Several open source Java libraries are used to pre-process the image and extract the textual information. The results are presented in an Excel table together with the outcome of several consistency checks. After manually correcting potential errors, the outcome is automatically stored in the main database. The proposed system yielded excellent results, reaching an accuracy of 99.94% and reducing the necessary human effort to a minimum.

  @article{reul2016expectationdriven, abstract = {In this study an expectation-driven approach is proposed to extract data stored as pixel structures in medical ultrasound images. Prior knowledge about certain properties like the position of the text and its background and foreground grayscale values is utilized. Several open source Java libraries are used to pre-process the image and extract the textual information. The results are presented in an Excel table together with the outcome of several consistency checks. After manually correcting potential errors, the outcome is automatically stored in the main database. The proposed system yielded excellent results, reaching an accuracy of 99.94% and reducing the necessary human effort to a minimum.}, author = {Reul, Christian and Köberle, Philipp and Üçeyler, Nurcan and Puppe, Frank}, journal = {Studies in Health Technology and Informatics}, keywords = {myown}, title = {Expectation-driven Text Extraction from Medical Ultrasound Images}, year = 2016 }
• 
  What Makes a Link Successful on Wikipedia? Dimitrov, Dimitar; Singer, Philipp; Lemmerich, Florian; Strohmaier, Markus in CoRR (2016). abs/1611.02508
  • [ BibTeX ]
  @article{dimitrov2016, author = {Dimitrov, Dimitar and Singer, Philipp and Lemmerich, Florian and Strohmaier, Markus}, journal = {CoRR}, keywords = {wikipedia}, title = {What Makes a Link Successful on Wikipedia?}, volume = {abs/1611.02508}, year = 2016 }
• 
  Cross Dataset Evaluation of Feature Extraction Techniques for Leaf Classification Reul, Christian; Toepfer, Martin; Puppe, Frank in International Journal of Artificial Intelligence & Applications (2016).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  In this work feature extraction techniques for leaf classification are evaluated in a cross dataset scenario. First, a leaf identification system consisting of six feature classes is described and tested on five established publicly available datasets by using standard evaluation procedures within the datasets. Afterwards, the performance of the developed system is evaluated in the much more challenging scenario of cross dataset evaluation. Finally, a new dataset is introduced as well as a web service, which allows to identify leaves both photographed on paper and when still attached to the tree. While the results obtained during classification within a dataset come close to the state of the art, the classification accuracy in cross dataset evaluation is significantly worse. However, by adjusting the system and taking the top five predictions into consideration very good results of up to 98% are achieved. It is shown that this difference is down to the ineffectiveness of certain feature classes as well as the increased severity of the task as leaves that grew under different environmental influences can differ significantly not only in colour, but also in shape.

  @article{reul2016cross, abstract = {In this work feature extraction techniques for leaf classification are evaluated in a cross dataset scenario. First, a leaf identification system consisting of six feature classes is described and tested on five established publicly available datasets by using standard evaluation procedures within the datasets. Afterwards, the performance of the developed system is evaluated in the much more challenging scenario of cross dataset evaluation. Finally, a new dataset is introduced as well as a web service, which allows to identify leaves both photographed on paper and when still attached to the tree. While the results obtained during classification within a dataset come close to the state of the art, the classification accuracy in cross dataset evaluation is significantly worse. However, by adjusting the system and taking the top five predictions into consideration very good results of up to 98% are achieved. It is shown that this difference is down to the ineffectiveness of certain feature classes as well as the increased severity of the task as leaves that grew under different environmental influences can differ significantly not only in colour, but also in shape.}, author = {Reul, Christian and Toepfer, Martin and Puppe, Frank}, journal = {International Journal of Artificial Intelligence & Applications}, keywords = {segmentation}, title = {Cross Dataset Evaluation of Feature Extraction Techniques for Leaf Classification}, year = 2016 }
• 
  Autonomous Quadrocopter for Search, Count and Localization of Objects Gageik, Nils; Reul, Christian; Montenegro, Sergio in Recent Advances in Robotic Systems (2016).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  This chapter describes and evaluates the design and implementation of a new fully autonomous quadrocopter, which is capable of self-reliant search, count and localization of a predefined object on the ground inside a room. In a preliminary calibration scan the parameters of the object are defined: As an example object a red ball is used. The scan determines the colour and radius of the ball. The implementation and principles of the object recognition and search will be described in detail. After determining the scanning parameters, the autonomous search can be executed. This is done autonomously by the quadrocopter, which uses inertial, infrared, ultrasonic, pressure sensors and an optical flow sensor to determine and control its orientation and position in 6 DOF (degree of freedom). Furthermore the quadrocopter can be equipped with sensors for obstacle detection and collision avoidance such as ultrasonic, infrared, pmd (photo mixing device) and sv (stereo vision) cameras. A camera attached to the quadrocopter and directed at the ground is used to find the searched objects and to determine its positions during the autonomous flight. Hence, objects which fulfil the scanning parameters can be found in different positions. Based on its own known position and the position of the object in the picture of the camera, the position of the detected objects can be determined. Thus repeated detections of objects can be excluded. Consequently, objects can be counted and localized autonomously. The position of the object is transferred to the ground station and compared with the true position to evaluate the system. Two different search situations and two different strategies, breadth first search (BFS) and depth first search (DFS), are investigated and their results are compared. The evaluation shows the potential, constraints and drawbacks of this approach just as the effect of the search strategy, and the most important parameters and indicators such as field of view, masking area and minimal object distance as well as accuracy, performance and completeness of the search. The entire system is composed of low-cost components and constructed from scratch. Its integration in the innovative real-time operating system Rodos developed by the German Aerospace Centre is described in detail. Rodos has been developed for embedded systems such as satellites and comparable aerospace systems.

  @inbook{nils2016autonomous, abstract = {This chapter describes and evaluates the design and implementation of a new fully autonomous quadrocopter, which is capable of self-reliant search, count and localization of a predefined object on the ground inside a room. In a preliminary calibration scan the parameters of the object are defined: As an example object a red ball is used. The scan determines the colour and radius of the ball. The implementation and principles of the object recognition and search will be described in detail. After determining the scanning parameters, the autonomous search can be executed. This is done autonomously by the quadrocopter, which uses inertial, infrared, ultrasonic, pressure sensors and an optical flow sensor to determine and control its orientation and position in 6 DOF (degree of freedom). Furthermore the quadrocopter can be equipped with sensors for obstacle detection and collision avoidance such as ultrasonic, infrared, pmd (photo mixing device) and sv (stereo vision) cameras. A camera attached to the quadrocopter and directed at the ground is used to find the searched objects and to determine its positions during the autonomous flight. Hence, objects which fulfil the scanning parameters can be found in different positions. Based on its own known position and the position of the object in the picture of the camera, the position of the detected objects can be determined. Thus repeated detections of objects can be excluded. Consequently, objects can be counted and localized autonomously. The position of the object is transferred to the ground station and compared with the true position to evaluate the system. Two different search situations and two different strategies, breadth first search (BFS) and depth first search (DFS), are investigated and their results are compared. The evaluation shows the potential, constraints and drawbacks of this approach just as the effect of the search strategy, and the most important parameters and indicators such as field of view, masking area and minimal object distance as well as accuracy, performance and completeness of the search. The entire system is composed of low-cost components and constructed from scratch. Its integration in the innovative real-time operating system Rodos developed by the German Aerospace Centre is described in detail. Rodos has been developed for embedded systems such as satellites and comparable aerospace systems.}, author = {Gageik, Nils and Reul, Christian and Montenegro, Sergio}, booktitle = {Recent Advances in Robotic Systems}, keywords = {myown}, title = {Autonomous Quadrocopter for Search, Count and Localization of Objects}, year = 2016 }
• 
  Collaborative Decision Support and Documentation in Chemical Safety with {KnowSEC} Baumeister, Joachim; Striffler, Albrecht; Brandt, Marc; Neumann, Michael in Journal of Cheminformatics (2016). 8(21) 1–16.
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  To protect the health of human and environment, the European Union implemented the REACH regulation for chemical substances. REACH is an acronym for Registration, Evaluation, Authorization, and Restriction of Chemicals. Under REACH, the authorities have the task of assessing chemical substances, especially those that might pose a risk to human health or environment. The work under REACH is scientifically, technically and procedurally a complex and knowledge-intensive task that is jointly performed by the European Chemicals Agency and member state authorities in Europe. The assessment of substances under REACH conducted in the German Environment Agency is supported by the knowledge-based system KnowSEC, which is used for the screening, documentation, and decision support when working on chemical substances. The software KnowSEC integrates advanced semantic technologies and strong problem solving methods. It allows for the collaborative work on substances in the context of the European REACH regulation. We discuss the applied methods and process models and we report on experiences with the implementation and use of the system.

  @article{baumeister2016collaborative, abstract = {To protect the health of human and environment, the European Union implemented the REACH regulation for chemical substances. REACH is an acronym for Registration, Evaluation, Authorization, and Restriction of Chemicals. Under REACH, the authorities have the task of assessing chemical substances, especially those that might pose a risk to human health or environment. The work under REACH is scientifically, technically and procedurally a complex and knowledge-intensive task that is jointly performed by the European Chemicals Agency and member state authorities in Europe. The assessment of substances under REACH conducted in the German Environment Agency is supported by the knowledge-based system KnowSEC, which is used for the screening, documentation, and decision support when working on chemical substances. The software KnowSEC integrates advanced semantic technologies and strong problem solving methods. It allows for the collaborative work on substances in the context of the European REACH regulation. We discuss the applied methods and process models and we report on experiences with the implementation and use of the system.}, author = {Baumeister, Joachim and Striffler, Albrecht and Brandt, Marc and Neumann, Michael}, journal = {Journal of Cheminformatics}, keywords = {rokt}, number = 21, pages = {1-16}, title = {Collaborative Decision Support and Documentation in Chemical Safety with {KnowSEC}}, volume = 8, year = 2016 }
• 
  What Users Actually do in a Social Tagging System: A Study of User Behavior in BibSonomy Doerfel, Stephan; Zoller, Daniel; Singer, Philipp; Niebler, Thomas; Hotho, Andreas; Strohmaier, Markus in ACM Transactions on the Web (2016). 10(2) 14:1–14:32.
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  Social tagging systems have established themselves as an important part in today’s web and have attracted the interest of our research community in a variety of investigations. Henceforth, several aspects of social tagging systems have been discussed and assumptions have emerged on which our community builds their work. Yet, testing such assumptions has been difficult due to the absence of suitable usage data in the past. In this work, we thoroughly investigate and evaluate four aspects about tagging systems, covering social interaction, retrieval of posted resources, the importance of the three different types of entities, users, resources, and tags, as well as connections between these entities’ popularity in posted and in requested content. For that purpose, we examine live server log data gathered from the real-world, public social tagging system BibSonomy. Our empirical results paint a mixed picture about the four aspects. While for some, typical assumptions hold to a certain extent, other aspects need to be reflected in a very critical light. Our observations have implications for the understanding of social tagging systems, and the way they are used on the web. We make the dataset used in this work available to other researchers.

  @article{doerfel2016users, abstract = {Social tagging systems have established themselves as an important part in today’s web and have attracted the interest of our research community in a variety of investigations. Henceforth, several aspects of social tagging systems have been discussed and assumptions have emerged on which our community builds their work. Yet, testing such assumptions has been difficult due to the absence of suitable usage data in the past. In this work, we thoroughly investigate and evaluate four aspects about tagging systems, covering social interaction, retrieval of posted resources, the importance of the three different types of entities, users, resources, and tags, as well as connections between these entities’ popularity in posted and in requested content. For that purpose, we examine live server log data gathered from the real-world, public social tagging system BibSonomy. Our empirical results paint a mixed picture about the four aspects. While for some, typical assumptions hold to a certain extent, other aspects need to be reflected in a very critical light. Our observations have implications for the understanding of social tagging systems, and the way they are used on the web. We make the dataset used in this work available to other researchers.}, author = {Doerfel, Stephan and Zoller, Daniel and Singer, Philipp and Niebler, Thomas and Hotho, Andreas and Strohmaier, Markus}, journal = {ACM Transactions on the Web}, keywords = {published}, number = 2, pages = {14:1–14:32}, title = {What Users Actually do in a Social Tagging System: A Study of User Behavior in BibSonomy}, volume = 10, year = 2016 }
• 
  Web-PaDaWaN: Eine Web-basierte Benutzeroberfläche für ein klinisches Data Warehouse Dietrich, Georg; Fell, Friedreich; Fette, Georg; Krebs, Jonathan; Ertl, Maximilian; Kaspar, Mathias; Störk, Stefan (2016).
  • [ BibTeX ]
  • [ URL ]
  @article{dietrich2016webpadawan, author = {Dietrich, Georg and Fell, Friedreich and Fette, Georg and Krebs, Jonathan and Ertl, Maximilian and Kaspar, Mathias and Störk, Stefan}, keywords = {myown}, month = {August}, title = {Web-PaDaWaN: Eine Web-basierte Benutzeroberfläche für ein klinisches Data Warehouse}, year = 2016 }
• 
  FolkTrails: Interpreting Navigation Behavior in a Social Tagging System Niebler, Thomas; Becker, Martin; Zoller, Daniel; Doerfel, Stephan; Hotho, Andreas in Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, CIKM ’16 (2016).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  Social tagging systems have established themselves as a quick and easy way to organize information by annotating resources with tags. In recent work, user behavior in social tagging systems was studied, that is, how users assign tags, and consume content. However, it is still unclear how users make use of the navigation options they are given. Understanding their behavior and differences in behavior of different user groups is an important step towards assessing the effectiveness of a navigational concept and of improving it to better suit the users’ needs. In this work, we investigate navigation trails in the popular scholarly social tagging system BibSonomy from six years of log data. We discuss dynamic browsing behavior of the general user population and show that different navigational subgroups exhibit different navigational traits. Furthermore, we provide strong evidence that the semantic nature of the underlying folksonomy is an essential factor for explaining navigation.

  @inproceedings{niebler2016folktrails, abstract = {Social tagging systems have established themselves as a quick and easy way to organize information by annotating resources with tags. In recent work, user behavior in social tagging systems was studied, that is, how users assign tags, and consume content. However, it is still unclear how users make use of the navigation options they are given. Understanding their behavior and differences in behavior of different user groups is an important step towards assessing the effectiveness of a navigational concept and of improving it to better suit the users’ needs. In this work, we investigate navigation trails in the popular scholarly social tagging system BibSonomy from six years of log data. We discuss dynamic browsing behavior of the general user population and show that different navigational subgroups exhibit different navigational traits. Furthermore, we provide strong evidence that the semantic nature of the underlying folksonomy is an essential factor for explaining navigation.}, author = {Niebler, Thomas and Becker, Martin and Zoller, Daniel and Doerfel, Stephan and Hotho, Andreas}, booktitle = {Proceedings of the 25th ACM International on Conference on Information and Knowledge Management}, keywords = {semantics}, publisher = {ACM}, series = {CIKM '16}, title = {FolkTrails: Interpreting Navigation Behavior in a Social Tagging System}, year = 2016 }
• 
  Fast exhaustive subgroup discovery with numerical target concepts Lemmerich, Florian; Atzmueller, Martin; Puppe, Frank in Data Mining and Knowledge Discovery (2016). 30(3) 711–762.
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  Subgroup discovery is a key data mining method that aims at identifying descriptions of subsets of the data that show an interesting distribution with respect to a pre-defined target concept. For practical applications the integration of numerical data is crucial. Therefore, a wide variety of interestingness measures has been proposed in literature that use a numerical attribute as the target concept. However, efficient mining in this setting is still an open issue. In this paper, we present novel techniques for fast exhaustive subgroup discovery with a numerical target concept. We initially survey previously proposed measures in this setting. Then, we explore options for pruning the search space using optimistic estimate bounds. Specifically, we introduce novel bounds in closed form and ordering-based bounds as a new technique to derive estimates for several types of interestingness measures with no previously known bounds. In addition, we investigate efficient data structures, namely adapted FP-trees and bitset-based data representations, and discuss their interdependencies to interestingness measures and pruning schemes. The presented techniques are incorporated into two novel algorithms. Finally, the benefits of the proposed pruning bounds and algorithms are assessed and compared in an extensive experimental evaluation on 24 publicly available datasets. The novel algorithms reduce runtimes consistently by more than one order of magnitude.

  @article{Lemmerich2016, abstract = {Subgroup discovery is a key data mining method that aims at identifying descriptions of subsets of the data that show an interesting distribution with respect to a pre-defined target concept. For practical applications the integration of numerical data is crucial. Therefore, a wide variety of interestingness measures has been proposed in literature that use a numerical attribute as the target concept. However, efficient mining in this setting is still an open issue. In this paper, we present novel techniques for fast exhaustive subgroup discovery with a numerical target concept. We initially survey previously proposed measures in this setting. Then, we explore options for pruning the search space using optimistic estimate bounds. Specifically, we introduce novel bounds in closed form and ordering-based bounds as a new technique to derive estimates for several types of interestingness measures with no previously known bounds. In addition, we investigate efficient data structures, namely adapted FP-trees and bitset-based data representations, and discuss their interdependencies to interestingness measures and pruning schemes. The presented techniques are incorporated into two novel algorithms. Finally, the benefits of the proposed pruning bounds and algorithms are assessed and compared in an extensive experimental evaluation on 24 publicly available datasets. The novel algorithms reduce runtimes consistently by more than one order of magnitude.}, author = {Lemmerich, Florian and Atzmueller, Martin and Puppe, Frank}, journal = {Data Mining and Knowledge Discovery}, keywords = {subgroup}, number = 3, pages = {711–762}, title = {Fast exhaustive subgroup discovery with numerical target concepts}, volume = 30, year = 2016 }

• 
  Entanglement formation under random interactions Wick, Christoph; Um, Jaegon; Hinrichsen, Haye (2015).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  The temporal evolution of the entanglement between two qubits evolving by random interactions is studied analytically and numerically. Two different types of randomness are investigated. Firstly we analyze an ensemble of systems with randomly chosen but time-independent interaction Hamiltonians. Secondly we consider the case of a temporally fluctuating Hamiltonian, where the unitary evolution can be understood as a random walk on the SU (4) group manifold. As a by-product we compute the metric tensor and its inverse as well as the Laplace-Beltrami for SU (4).

  @misc{wick2015entanglement, abstract = {The temporal evolution of the entanglement between two qubits evolving by random interactions is studied analytically and numerically. Two different types of randomness are investigated. Firstly we analyze an ensemble of systems with randomly chosen but time-independent interaction Hamiltonians. Secondly we consider the case of a temporally fluctuating Hamiltonian, where the unitary evolution can be understood as a random walk on the SU (4) group manifold. As a by-product we compute the metric tensor and its inverse as well as the Laplace-Beltrami for SU (4).}, author = {Wick, Christoph and Um, Jaegon and Hinrichsen, Haye}, keywords = {myown}, note = {cite arxiv:1508.01652v2.pdfComment: Latex, 24 pages, 4 figures, Supplement material in source archive}, title = {Entanglement formation under random interactions}, year = 2015 }
• 
  {Selbstlernende Wissensbasen in der Kataraktchirurgie} Scherer, Klaus Peter; Rieder, Constantin; Henninger, Christian; Knoell, Daniel; Baumeister, Joachim; Furth, Sebastian in Spektrum der Augenheilkunde (2015). 29(2) 75–76.
  • [ BibTeX ]
  @article{scherer2015selbstlernende, author = {Scherer, Klaus Peter and Rieder, Constantin and Henninger, Christian and Knoell, Daniel and Baumeister, Joachim and Furth, Sebastian}, journal = {Spektrum der Augenheilkunde}, keywords = {selesup}, month = {February}, number = 2, pages = {75-76}, title = {{Selbstlernende Wissensbasen in der Kataraktchirurgie}}, volume = 29, year = 2015 }
• 
  Extraktion von Lungenfunktionsparametern aus Arztbriefen Toepfer, Martin; Schmidt, David; Dietrich, Georg; Ertl, Max; Fette, Georg; Kaspar, Mathias; Störk, Stefan; Puppe, Frank (2015).
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  @article{20feea2d-bdb3-45c8-b63d-d172de0f22c1, author = {Toepfer, Martin and Schmidt, David and Dietrich, Georg and Ertl, Max and Fette, Georg and Kaspar, Mathias and Störk, Stefan and Puppe, Frank}, keywords = {myown}, publisher = {German Medical Science GMS Publishing House}, title = {Extraktion von Lungenfunktionsparametern aus Arztbriefen}, year = 2015 }
• 
  Extraktion und Transfer patientenbezogener Daten aus klinischen Informationssystemen in Studiendatenbanken - effektive Unterstützung klinisch-epidemiologischer Forschung durch ein Data Warehouse Kaspar, Mathias; Fette, Georg; Ertl, Max; Dietrich, Georg; Nagler, Nils; Störk, Stefan; Angermann, Christiane; Puppe, Frank (2015).
  • [ BibTeX ]
  • [ URL ]
  @article{096855bc-4f18-44ee-ba5b-cd39285c07dc, author = {Kaspar, Mathias and Fette, Georg and Ertl, Max and Dietrich, Georg and Nagler, Nils and Störk, Stefan and Angermann, Christiane and Puppe, Frank}, keywords = {myown}, publisher = {German Medical Science GMS Publishing House}, title = {Extraktion und Transfer patientenbezogener Daten aus klinischen Informationssystemen in Studiendatenbanken - effektive Unterstützung klinisch-epidemiologischer Forschung durch ein Data Warehouse}, year = 2015 }
• 
  Fallstudie zur Validierung eines klinischen Data-Warehouse mit Hintergrundwissen Dietrich, Georg; Fette, Georg; Ertl, Max; Toepfer, Martin; Kaspar, Mathias; Störk, Stefan; Puppe, Frank (2015).
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  @article{da6083c9-5d88-4363-9bc1-6b46583ba1c3, author = {Dietrich, Georg and Fette, Georg and Ertl, Max and Toepfer, Martin and Kaspar, Mathias and Störk, Stefan and Puppe, Frank}, keywords = {myown}, publisher = {German Medical Science GMS Publishing House}, title = {Fallstudie zur Validierung eines klinischen Data-Warehouse mit Hintergrundwissen}, year = 2015 }
• 
  Die grafische Benutzeroberfläche PaDaWaN für das klinische Data Warehouse für Routinedaten an der Universitätsklinik Würzburg Fette, Georg; Dietrich, Georg; Ertl, Max; Toepfer, Martin; Kaspar, Mathias; Störk, Stefan; Puppe, Frank (2015).
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  @article{06251677-6ed5-4974-bbd3-64a0e6158fdc, author = {Fette, Georg and Dietrich, Georg and Ertl, Max and Toepfer, Martin and Kaspar, Mathias and Störk, Stefan and Puppe, Frank}, keywords = {myown}, publisher = {German Medical Science GMS Publishing House}, title = {Die grafische Benutzeroberfläche PaDaWaN für das klinische Data Warehouse für Routinedaten an der Universitätsklinik Würzburg}, year = 2015 }
• 
  ConDist: A Context-Driven Categorical Distance Measure Ring, Markus; Otto, Florian; Becker, Martin; Niebler, Thomas; Landes, Dieter; Hotho, Andreas in Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, Lecture Notes in Computer Science, A. Appice, P. P. Rodrigues, V. S. Costa, C. Soares, J. Gama, A. Jorge (eds.) (2015). (Vol. 9284) 251–266.
  • [ Abstract ]
  • [ BibTeX ]
  • [ Download ]
  A distance measure between objects is a key requirement for many data mining tasks like clustering, classification or outlier detection. However, for objects characterized by categorical attributes, defining meaningful distance measures is a challenging task since the values within such attributes have no inherent order, especially without additional domain knowledge. In this paper, we propose an unsupervised distance measure for objects with categorical attributes based on the idea that categorical attribute values are similar if they appear with similar value distributions on correlated context attributes. Thus, the distance measure is automatically derived from the given data set. We compare our new distance measure to existing categorical distance measures and evaluate on different data sets from the UCI machine-learning repository. The experiments show that our distance measure is recommendable, since it achieves similar or better results in a more robust way than previous approaches.

  @inproceedings{ring2015condist, abstract = {A distance measure between objects is a key requirement for many data mining tasks like clustering, classification or outlier detection. However, for objects characterized by categorical attributes, defining meaningful distance measures is a challenging task since the values within such attributes have no inherent order, especially without additional domain knowledge. In this paper, we propose an unsupervised distance measure for objects with categorical attributes based on the idea that categorical attribute values are similar if they appear with similar value distributions on correlated context attributes. Thus, the distance measure is automatically derived from the given data set. We compare our new distance measure to existing categorical distance measures and evaluate on different data sets from the UCI machine-learning repository. The experiments show that our distance measure is recommendable, since it achieves similar or better results in a more robust way than previous approaches.}, author = {Ring, Markus and Otto, Florian and Becker, Martin and Niebler, Thomas and Landes, Dieter and Hotho, Andreas}, booktitle = {Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases}, editor = {Appice, Annalisa and Rodrigues, Pedro Pereira and Costa, Vítor Santos and Soares, Carlos and Gama, João and Jorge, Alípio}, keywords = {published}, pages = {251-266}, publisher = {Springer International Publishing}, series = {Lecture Notes in Computer Science}, title = {ConDist: A Context-Driven Categorical Distance Measure}, volume = 9284, year = 2015 }
• 
  Extracting Semantic Relatedness from Navigation in a Social Tagging System Niebler, Thomas; Becker, Martin; Zoller, Daniel; Doerfel, Stephan; Hotho, Andreas (2015).
  • [ BibTeX ]
  @techreport{tr_niebler2015extracting, author = {Niebler, Thomas and Becker, Martin and Zoller, Daniel and Doerfel, Stephan and Hotho, Andreas}, keywords = {semantics}, title = {Extracting Semantic Relatedness from Navigation in a Social Tagging System}, year = 2015 }
• 
  Fine-grained information extraction from German transthoracic echocardiography reports. Toepfer, Martin; Corovic, Hamo; Fette, Georg; Klügl, Peter; Störk, Stefan; Puppe, Frank in BMC Med. Inf. & Decision Making (2015). 15 91.
  • [ BibTeX ]
  • [ URL ]
  @article{journals/midm/ToepferCFKSP15, author = {Toepfer, Martin and Corovic, Hamo and Fette, Georg and Klügl, Peter and Störk, Stefan and Puppe, Frank}, journal = {BMC Med. Inf. & Decision Making}, keywords = {myown}, pages = 91, title = {Fine-grained information extraction from German transthoracic echocardiography reports.}, volume = 15, year = 2015 }
• 
  VizTrails: An Information Visualization Tool for Exploring Geographic Movement Trajectories Becker, Martin; Singer, Philipp; Lemmerich, Florian; Hotho, Andreas; Helic, Denis; Strohmaier, Markus in Proceedings of the 26th ACM Conference on Hypertext \&\#38; Social Media, HT ’15 (2015). 319–320.
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  Understanding the way people move through urban areas represents an important problem that has implications for a range of societal challenges such as city planning, public transportation, or crime analysis. In this paper, we present an interactive visualization tool called VizTrails for exploring and understanding such human movement. It features visualizations that show aggregated statistics of trails for geographic areas that correspond to grid cells on a map, e.g., on the number of users passing through or on cells commonly visited next. Amongst other features, system allows to overlay the map with the results of SPARQL queries in order to relate the observed trajectory statistics with its geo-spatial context, e.g., considering a city's points of interest. The systems functionality is demonstrated using trajectory examples extracted from the social photo sharing platform Flickr. Overall, VizTrails facilitates deeper insights into geo-spatial trajectory data by enabling interactive exploration of aggregated statistics and providing geo-spatial context.

  @inproceedings{Becker:2015:VIV:2700171.2791021, abstract = {Understanding the way people move through urban areas represents an important problem that has implications for a range of societal challenges such as city planning, public transportation, or crime analysis. In this paper, we present an interactive visualization tool called VizTrails for exploring and understanding such human movement. It features visualizations that show aggregated statistics of trails for geographic areas that correspond to grid cells on a map, e.g., on the number of users passing through or on cells commonly visited next. Amongst other features, system allows to overlay the map with the results of SPARQL queries in order to relate the observed trajectory statistics with its geo-spatial context, e.g., considering a city's points of interest. The systems functionality is demonstrated using trajectory examples extracted from the social photo sharing platform Flickr. Overall, VizTrails facilitates deeper insights into geo-spatial trajectory data by enabling interactive exploration of aggregated statistics and providing geo-spatial context.}, address = {New York, NY, USA}, author = {Becker, Martin and Singer, Philipp and Lemmerich, Florian and Hotho, Andreas and Helic, Denis and Strohmaier, Markus}, booktitle = {Proceedings of the 26th ACM Conference on Hypertext \&\#38; Social Media}, keywords = {visualization}, pages = {319–320}, publisher = {ACM}, series = {HT '15}, title = {VizTrails: An Information Visualization Tool for Exploring Geographic Movement Trajectories}, year = 2015 }
• 
  Knowledge-Driven Systems for Episodic Decision Support Baumeister, Joachim; Striffler, Albrecht in Knowledge-Based Systems (2015). 88 45–56.
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  @article{baumeister2015knowledgedriven, author = {Baumeister, Joachim and Striffler, Albrecht}, journal = {Knowledge-Based Systems}, keywords = {sysrelevantforuniwueinfo6}, month = {November}, pages = {45-56}, title = {Knowledge-Driven Systems for Episodic Decision Support}, volume = 88, year = 2015 }
• 
  Decision Support for Ophthalmic Applications Scherer, Klaus-Peter; Germann, Markus; Baumeister, Joachim; Furth, Sebastian in 23rd International Conference on Multiple Criteria Decision Making (2015). 132–133.
  • [ BibTeX ]
  @inproceedings{scherer2015decision, author = {Scherer, Klaus-Peter and Germann, Markus and Baumeister, Joachim and Furth, Sebastian}, booktitle = {23rd International Conference on Multiple Criteria Decision Making}, keywords = {semanticwiki}, pages = {132-133}, title = {Decision Support for Ophthalmic Applications}, year = 2015 }
• 
  On the Semantification of 5-Star Technical Documentation Furth, Sebastian; Baumeister, Joachim in Proceedings of the LWA 2015 Workshops: KDML, FGWM, IR, and FGDB, CEUR Workshop Proceedings, R. Bergmann, S. Görg, G. Müller (eds.) (2015). (Vol. 1458) 264–271.
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  @inproceedings{FB:LWA:15, author = {Furth, Sebastian and Baumeister, Joachim}, booktitle = {Proceedings of the LWA 2015 Workshops: KDML, FGWM, IR, and FGDB}, editor = {Bergmann, Ralph and Görg, Sebastian and Müller, Gilbert}, keywords = {rokt}, pages = {264-271}, publisher = {CEUR-WS.org}, series = {CEUR Workshop Proceedings}, title = {On the Semantification of 5-Star Technical Documentation}, volume = 1458, year = 2015 }
• 
  Towards Context-Aware Technical Service Legler, Alexander; Baumeister, Joachim in Proceedings of the LWA 2015 Workshops: KDML, FGWM, IR, and FGDB, CEUR Workshop Proceedings, R. Bergmann, S. Görg, G. Müller (eds.) (2015). (Vol. 1458) 288–295.
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  @inproceedings{conf/lwa/LeglerB15, author = {Legler, Alexander and Baumeister, Joachim}, booktitle = {Proceedings of the LWA 2015 Workshops: KDML, FGWM, IR, and FGDB}, editor = {Bergmann, Ralph and Görg, Sebastian and Müller, Gilbert}, keywords = {rokt}, pages = {288-295}, publisher = {CEUR-WS.org}, series = {CEUR Workshop Proceedings}, title = {Towards Context-Aware Technical Service}, volume = 1458, year = 2015 }
• 
  Automatische Erkennung von Figuren in deutschsprachigen Romanen Fotis, Jannidis; Krug, Markus; Puppe, Frank; Toepfer, Martin; Weimer, Lukas; Reger, Isabella (2015).
  • [ BibTeX ]
  @conference{fotis2015automatische, author = {Fotis, Jannidis and Krug, Markus and Puppe, Frank and Toepfer, Martin and Weimer, Lukas and Reger, Isabella}, keywords = {novel}, title = {Automatische Erkennung von Figuren in deutschsprachigen Romanen}, year = 2015 }
• 
  Rule based Coreference Resolution in German Historic Novels Puppe, Frank; Krug, Markus; Jannidis, Fotis; Reger, Isabella; Weimer, Lukas; Macharowsky, Luisa (2015).
  • [ BibTeX ]
  @conference{noauthororeditor2015based, author = {Puppe, Frank and Krug, Markus and Jannidis, Fotis and Reger, Isabella and Weimer, Lukas and Macharowsky, Luisa}, keywords = {myown}, title = {Rule based Coreference Resolution in German Historic Novels}, year = 2015 }
• 
  Fine-grained information extraction from German transthoracic echocardiography reports Toepfer, Martin; Corovic, Hamo; Fette, Georg; Klügl, Peter; Störk, Stefan; Puppe, Frank in BMC Medical Informatics and Decision Making (2015). 15 103.
  • [ BibTeX ]
  • [ URL ]
  @article{Toepfer2015, author = {Toepfer, Martin and Corovic, Hamo and Fette, Georg and Klügl, Peter and Störk, Stefan and Puppe, Frank}, journal = {BMC Medical Informatics and Decision Making}, keywords = {myown}, pages = 103, title = {Fine-grained information extraction from German transthoracic echocardiography reports}, volume = 15, year = 2015 }
• 
  Evaluating Emergent Semantics in Folksonomies on Human Intuition Niebler, Thomas; Becker, Martin; Zoller, Daniel; Doerfel, Stephan; Hotho, Andreas (2015).
  • [ BibTeX ]
  • [ Download ]
  @techreport{tr_niebler2015evaluating, author = {Niebler, Thomas and Becker, Martin and Zoller, Daniel and Doerfel, Stephan and Hotho, Andreas}, keywords = {wordnet}, title = {Evaluating Emergent Semantics in Folksonomies on Human Intuition}, year = 2015 }

• 
  UIMA Ruta: Rapid development of rule-based information extraction applications Kluegl, Peter; Toepfer, Martin; Beck, Philip-Daniel; Fette, Georg; Puppe, Frank in Natural Language Engineering (2014). FirstView 1–40.
  • [ BibTeX ]
  • [ URL ]
  @article{NLE:9375265, author = {Kluegl, Peter and Toepfer, Martin and Beck, Philip-Daniel and Fette, Georg and Puppe, Frank}, journal = {Natural Language Engineering}, keywords = {uima}, month = 10, pages = {1–40}, title = {UIMA Ruta: Rapid development of rule-based information extraction applications}, volume = {FirstView}, year = 2014 }
• 
  TELESUP - Textual Self-Learning Support Systems Furth, Sebastian; Baumeister, Joachim in FGWM’14: Proceedings of German Workshop of Knowledge and Experience Management at LWA’2014 (2014).
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{furth2014telesup, author = {Furth, Sebastian and Baumeister, Joachim}, booktitle = {FGWM'14: Proceedings of German Workshop of Knowledge and Experience Management at LWA'2014}, keywords = {ontology}, title = {TELESUP - Textual Self-Learning Support Systems}, year = 2014 }
• 
  UIMA Ruta Workbench: Rule-based Text Annotation. Klügl, Peter; Toepfer, Martin; Beck, Philip-Daniel; Fette, Georg; Puppe, Frank in COLING (Demos), L. Tounsi, R. Rak (eds.) (2014). 29–33.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{conf/coling/KluglTBFP14, author = {Klügl, Peter and Toepfer, Martin and Beck, Philip-Daniel and Fette, Georg and Puppe, Frank}, booktitle = {COLING (Demos)}, crossref = {conf/coling/2014d}, editor = {Tounsi, Lamia and Rak, Rafal}, keywords = {myown}, pages = {29-33}, publisher = {ACL}, title = {UIMA Ruta Workbench: Rule-based Text Annotation.}, year = 2014 }
• 
  Integrated Tools for Query-driven Development of Light-weight Ontologies and Information Extraction Components Toepfer, Martin; Fette, Georg; Beck, Philip-Daniel; Klügl, Peter; Puppe, Frank in Proceedings of the Workshop on Open Infrastructures and Analysis Frameworks for HLT (2014). 83–92.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{Toepfer2014, address = {Dublin, Ireland}, author = {Toepfer, Martin and Fette, Georg and Beck, Philip-Daniel and Klügl, Peter and Puppe, Frank}, booktitle = {Proceedings of the Workshop on Open Infrastructures and Analysis Frameworks for HLT}, keywords = {myown}, pages = {83–92}, title = {Integrated Tools for Query-driven Development of Light-weight Ontologies and Information Extraction Components}, year = 2014 }
• 
  Spreadsheet-based Knowledge Acquisition for Facilitating Active Domain Expert Participation Freiberg, Martina; Herrmann, Felix; Puppe, Frank in Proceedings of the 19th European Conference on Knowledge Engineering and Knowledge Management (EKAW) - to appear (2014).
  • [ BibTeX ]
  @inproceedings{freiberg2014spreadsheetbased, author = {Freiberg, Martina and Herrmann, Felix and Puppe, Frank}, booktitle = {Proceedings of the 19th European Conference on Knowledge Engineering and Knowledge Management (EKAW) - to appear}, keywords = {myown}, title = {Spreadsheet-based Knowledge Acquisition for Facilitating Active Domain Expert Participation}, year = 2014 }
• 
  Clarification KBS as Consultation-Justification Mash Ups --- Proposing A Novel Paradigm for All-in-One Knowledge-based Systems Freiberg, Martina; Herrmann, Felix; Puppe, Frank in Proceedings of the International Conference on Knowledge Engineering and Ontology Development, J. Filipe, J. Dietz, D. Aveiro (eds.) (2014).
  • [ BibTeX ]
  @inproceedings{freiberg2014clarification, author = {Freiberg, Martina and Herrmann, Felix and Puppe, Frank}, booktitle = {Proceedings of the International Conference on Knowledge Engineering and Ontology Development}, editor = {Filipe, Joaquim and Dietz, Jan and Aveiro, David}, keywords = {myown}, title = {Clarification KBS as Consultation-Justification Mash Ups — Proposing A Novel Paradigm for All-in-One Knowledge-based Systems}, year = 2014 }
• 
  Extraktion kodierter Daten aus textuellen Befundberichten: Eine Fallstudie zu Echokardiographieberichten Toepfer, M.; Beck, P.D.; Dietrich, G.; Ertl, M.; Fette, G.; Kluegl, P.; Störk, S.; Puppe, F. (2014).
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  @article{3edd6d94-782d-461b-b6d4-94cda8249b30, author = {Toepfer, M. and Beck, P.D. and Dietrich, G. and Ertl, M. and Fette, G. and Kluegl, P. and Störk, S. and Puppe, F.}, keywords = {myown}, publisher = {German Medical Science GMS Publishing House}, title = {Extraktion kodierter Daten aus textuellen Befundberichten: Eine Fallstudie zu Echokardiographieberichten}, year = 2014 }
• 
  A Comparison of Search Engine Technologies for a Clinical Data Warehouse. Dietrich, Georg; Fette, Georg; Puppe, Frank in LWA, CEUR Workshop Proceedings, T. Seidl, M. Hassani, C. Beecks (eds.) (2014). (Vol. 1226) 235–242.
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  @inproceedings{conf/lwa/DietrichFP14, author = {Dietrich, Georg and Fette, Georg and Puppe, Frank}, booktitle = {LWA}, crossref = {conf/lwa/2014}, editor = {Seidl, Thomas and Hassani, Marwan and Beecks, Christian}, keywords = {myown}, pages = {235-242}, publisher = {CEUR-WS.org}, series = {CEUR Workshop Proceedings}, title = {A Comparison of Search Engine Technologies for a Clinical Data Warehouse.}, volume = 1226, year = 2014 }
• 
  Anfrage-spezifische Validierung in einem Data Warehouse für klinische Routinedaten an der Universitätsklinik Würzburg Dietrich, G.; Fette, G.; Beck, P.D.; Ertl, M.; Toepfer, M.; Kluegl, P.; Kaspar, M.; Störk, S.; Puppe, F. (2014).
  • [ BibTeX ]
  • [ URL ]
  @article{22fa5b3f-e7a1-4272-a9bb-2002d67b8234, author = {Dietrich, G. and Fette, G. and Beck, P.D. and Ertl, M. and Toepfer, M. and Kluegl, P. and Kaspar, M. and Störk, S. and Puppe, F.}, keywords = {myown}, publisher = {German Medical Science GMS Publishing House}, title = {Anfrage-spezifische Validierung in einem Data Warehouse für klinische Routinedaten an der Universitätsklinik Würzburg}, year = 2014 }
• 
  Pattern-driven Knowledge Systems Engineering Freiberg, Martina; Puppe, Frank in Proceedings of 10th Workshop on Knowledge Engineering and Software Engineering (KESE10) co-located with 21st European Conference on Artificial Intelligence (ECAI 2014), G. J. Nalepa, J. Baumeister (eds.) (2014). (Vol. Vol. 1289)
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{freiberg2014patterndriven, author = {Freiberg, Martina and Puppe, Frank}, booktitle = {Proceedings of 10th Workshop on Knowledge Engineering and Software Engineering (KESE10) co-located with 21st European Conference on Artificial Intelligence (ECAI 2014)}, editor = {Nalepa, Grzegorz J. and Baumeister, Joachim}, keywords = {myown}, title = {Pattern-driven Knowledge Systems Engineering}, volume = {Vol. 1289}, year = 2014 }
• 
  Of course we share! Testing Assumptions about Social Tagging Systems Doerfel, Stephan; Zoller, Daniel; Singer, Philipp; Niebler, Thomas; Hotho, Andreas; Strohmaier, Markus (2014).
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  Social tagging systems have established themselves as an important part in today's web and have attracted the interest from our research community in a variety of investigations. The overall vision of our community is that simply through interactions with the system, i.e., through tagging and sharing of resources, users would contribute to building useful semantic structures as well as resource indexes using uncontrolled vocabulary not only due to the easy-to-use mechanics. Henceforth, a variety of assumptions about social tagging systems have emerged, yet testing them has been difficult due to the absence of suitable data. In this work we thoroughly investigate three available assumptions - e.g., is a tagging system really social? - by examining live log data gathered from the real-world public social tagging system BibSonomy. Our empirical results indicate that while some of these assumptions hold to a certain extent, other assumptions need to be reflected and viewed in a very critical light. Our observations have implications for the design of future search and other algorithms to better reflect the actual user behavior.

  @techreport{doerfel2014course, abstract = {Social tagging systems have established themselves as an important part in today's web and have attracted the interest from our research community in a variety of investigations. The overall vision of our community is that simply through interactions with the system, i.e., through tagging and sharing of resources, users would contribute to building useful semantic structures as well as resource indexes using uncontrolled vocabulary not only due to the easy-to-use mechanics. Henceforth, a variety of assumptions about social tagging systems have emerged, yet testing them has been difficult due to the absence of suitable data. In this work we thoroughly investigate three available assumptions - e.g., is a tagging system really social? - by examining live log data gathered from the real-world public social tagging system BibSonomy. Our empirical results indicate that while some of these assumptions hold to a certain extent, other assumptions need to be reflected and viewed in a very critical light. Our observations have implications for the design of future search and other algorithms to better reflect the actual user behavior.}, author = {Doerfel, Stephan and Zoller, Daniel and Singer, Philipp and Niebler, Thomas and Hotho, Andreas and Strohmaier, Markus}, keywords = {testing}, note = {cite arxiv:1401.0629}, title = {Of course we share! Testing Assumptions about Social Tagging Systems}, year = 2014 }
• 
  {Prototypischer Einsatz eines Assistenzsystems in der Kataraktchirurgie} Scherer, Klaus Peter; Henninger, Christian; Rieder, Constantin; German, Markus; Baumeister, Joachim; Reutelshoefer, Jochen in Spektrum der Augenheilkunde (2014). 28(2) 66.
  • [ BibTeX ]
  @article{scherer2014prototypischer, author = {Scherer, Klaus Peter and Henninger, Christian and Rieder, Constantin and German, Markus and Baumeister, Joachim and Reutelshoefer, Jochen}, journal = {Spektrum der Augenheilkunde}, keywords = {myown}, number = 2, pages = 66, title = {{Prototypischer Einsatz eines Assistenzsystems in der Kataraktchirurgie}}, volume = 28, year = 2014 }
• 
  Integrated Tools for Query-driven Development of Light-weight Ontologies and Information Extraction Components Toepfer, Martin; Fette, Georg; Beck, Philip-Daniel; Klügl, Peter; Puppe, Frank in Proceedings of the Workshop on Open Infrastructures and Analysis Frameworks for HLT (2014). 83–92.
  • [ BibTeX ]
  @inproceedings{Toepfer2014, address = {Dublin, Ireland}, author = {Toepfer, Martin and Fette, Georg and Beck, Philip-Daniel and Klügl, Peter and Puppe, Frank}, booktitle = {Proceedings of the Workshop on Open Infrastructures and Analysis Frameworks for HLT}, keywords = {myown}, pages = {83–92}, title = {Integrated Tools for Query-driven Development of Light-weight Ontologies and Information Extraction Components}, year = 2014 }
• 
  Folksonomies Singer, Philipp; Niebler, Thomas; Hotho, Andreas; Strohmaier, Markus in Encyclopedia of Social Network Analysis and Mining (2014). 542–547.
  • [ BibTeX ]
  • [ Download ]
  @incollection{singer2014folksonomies, author = {Singer, Philipp and Niebler, Thomas and Hotho, Andreas and Strohmaier, Markus}, booktitle = {Encyclopedia of Social Network Analysis and Mining}, keywords = {published}, pages = {542–547}, publisher = {Springer}, title = {Folksonomies}, year = 2014 }
• 
  Kontext-sensitive Suche nach medizinischen Konzepten in Texten Liman, Leon (2014).
  • [ BibTeX ]
  @mastersthesis{liman2014kontextsensitive, author = {Liman, Leon}, editor = {Puppe, Frank}, keywords = {myown}, title = {Kontext-sensitive Suche nach medizinischen Konzepten in Texten}, year = 2014 }
• 
  UIMA Ruta Workbench: Rule-based Text Annotation Kluegl, Peter; Toepfer, Martin; Beck, Philip-Daniel; Fette, Georg; Puppe, Frank in Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: System Demonstrations (2014). 29–33.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{kluegl-EtAl:2014:ColingDemo, address = {Dublin, Ireland}, author = {Kluegl, Peter and Toepfer, Martin and Beck, Philip-Daniel and Fette, Georg and Puppe, Frank}, booktitle = {Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: System Demonstrations}, keywords = {workbench}, month = {August}, pages = {29–33}, publisher = {Dublin City University and Association for Computational Linguistics}, title = {UIMA Ruta Workbench: Rule-based Text Annotation}, year = 2014 }
• 
  Modeling and Visualization of Cataract Ontologies Scherer, Klaus Peter; Rieder, Constantin; Henninger, Christian; German, Markus; Baumeister, Joachim; Reutelshöfer, Jochen in ADVCOMP 2014: 8th International Conference on Advanced Engineering Computing and Applications in Sciences (2014).
  • [ BibTeX ]
  @inproceedings{scherer2014modeling, author = {Scherer, Klaus Peter and Rieder, Constantin and Henninger, Christian and German, Markus and Baumeister, Joachim and Reutelshöfer, Jochen}, booktitle = {ADVCOMP 2014: 8th International Conference on Advanced Engineering Computing and Applications in Sciences}, keywords = {visualization}, title = {Modeling and Visualization of Cataract Ontologies}, year = 2014 }
• 
  Declarative Evaluation of Ontologies with Rules Seipel, Dietmar; Baumeister, Joachim; Prätor, Klaus in Proceedings of the 28th Workshop on (Constraint) Logic Programming (WLP 2014) (2014). 53–65.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{seipel2014declarative, author = {Seipel, Dietmar and Baumeister, Joachim and Prätor, Klaus}, booktitle = {Proceedings of the 28th Workshop on (Constraint) Logic Programming (WLP 2014)}, keywords = {rule}, pages = {53–65}, title = {Declarative Evaluation of Ontologies with Rules}, year = 2014 }
• 
  The Connectivity of Multi-Modal Knowledge Bases Baumeister, Joachim; Reutelshoefer, Jochen in FGWM’14: Proceedings of German Workshop of Knowledge and Experience Management at LWA’2014 (2014).
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{baumeister2014connectivity, author = {Baumeister, Joachim and Reutelshoefer, Jochen}, booktitle = {FGWM'14: Proceedings of German Workshop of Knowledge and Experience Management at LWA'2014}, keywords = {ontology}, title = {The Connectivity of Multi-Modal Knowledge Bases}, year = 2014 }
• 
  How Social is Social Tagging? Doerfel, Stephan; Zoller, Daniel; Singer, Philipp; Niebler, Thomas; Strohmaier, Markus; Hotho, Andreas in Proceedings of the 23rd International World Wide Web Conference, WWW 2014 (2014). 251–252.
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  @inproceedings{doerfel2014social, author = {Doerfel, Stephan and Zoller, Daniel and Singer, Philipp and Niebler, Thomas and Strohmaier, Markus and Hotho, Andreas}, booktitle = {Proceedings of the 23rd International World Wide Web Conference}, keywords = {tagging}, pages = {251–252}, publisher = {ACM}, series = {WWW 2014}, title = {How Social is Social Tagging?}, year = 2014 }
• 
  Comprehensive visualization of paresthesia in breast cancer survivors Jud, SebastianM.; Hatko, Reinhard; Maihöfner, Christian; Bani, MayadaR.; Schrauder, MichaelG.; Lux, MichaelP.; Beckmann, MatthiasW.; Bani, Gassan; Eder, Irina; Fasching, PeterA.; Loehberg, ChristianR.; Rauh, Claudia; Hein, Alexander in Archives of Gynecology and Obstetrics (2014). 1–7.
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  As breast cancer survivors are benefiting increasingly from advanced forms of therapy, the side effects of locoregional treatment in the adjuvant setting are becoming more and more important. This article presents a new method of assessing the spatial distribution of paresthesia in breast cancer survivors after different locoregional treatments.

  @article{noKey, abstract = {As breast cancer survivors are benefiting increasingly from advanced forms of therapy, the side effects of locoregional treatment in the adjuvant setting are becoming more and more important. This article presents a new method of assessing the spatial distribution of paresthesia in breast cancer survivors after different locoregional treatments.}, author = {Jud, SebastianM. and Hatko, Reinhard and Maihöfner, Christian and Bani, MayadaR. and Schrauder, MichaelG. and Lux, MichaelP. and Beckmann, MatthiasW. and Bani, Gassan and Eder, Irina and Fasching, PeterA. and Loehberg, ChristianR. and Rauh, Claudia and Hein, Alexander}, journal = {Archives of Gynecology and Obstetrics}, keywords = {visualization}, pages = {1-7}, publisher = {Springer Berlin Heidelberg}, title = {Comprehensive visualization of paresthesia in breast cancer survivors}, year = 2014 }
• 
  An Ontology Debugger for the Semantic Wiki {KnowWE} Furth, Sebastian; Baumeister, Joachim in 10th Workshop on Knowledge Engineering and Software Engineering (KESE10) (2014).
  • [ BibTeX ]
  @inproceedings{furth2014ontology, author = {Furth, Sebastian and Baumeister, Joachim}, booktitle = {10th Workshop on Knowledge Engineering and Software Engineering (KESE10)}, keywords = {ontology}, title = {An Ontology Debugger for the Semantic Wiki {KnowWE}}, year = 2014 }

• 
  Computing Semantic Relatedness from Human Navigational Paths: A Case Study on Wikipedia Singer, Philipp; Niebler, Thomas; Strohmaier, Markus; Hotho, Andreas in IJSWIS (2013). 9(4) 41–70.
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  In this article, the authors present a novel approach for computing semantic relatedness and conduct a large-scale study of it on Wikipedia. Unlike existing semantic analysis methods that utilize Wikipedia’s content or link structure, the authors propose to use human navigational paths on Wikipedia for this task. The authors obtain 1.8 million human navigational paths from a semi-controlled navigation experiment – a Wikipedia-based navigation game, in which users are required to find short paths between two articles in a given Wikipedia article network. The authors’ results are intriguing: They suggest that (i) semantic relatedness computed from human navigational paths may be more precise than semantic relatedness computed from Wikipedia’s plain link structure alone and (ii) that not all navigational paths are equally useful. Intelligent selection based on path characteristics can improve accuracy. The authors’ work makes an argument for expanding the existing arsenal of data sources for calculating semantic relatedness and to consider the utility of human navigational paths for this task.

  @article{singer2013computing, abstract = {In this article, the authors present a novel approach for computing semantic relatedness and conduct a large-scale study of it on Wikipedia. Unlike existing semantic analysis methods that utilize Wikipedia’s content or link structure, the authors propose to use human navigational paths on Wikipedia for this task. The authors obtain 1.8 million human navigational paths from a semi-controlled navigation experiment – a Wikipedia-based navigation game, in which users are required to find short paths between two articles in a given Wikipedia article network. The authors’ results are intriguing: They suggest that (i) semantic relatedness computed from human navigational paths may be more precise than semantic relatedness computed from Wikipedia’s plain link structure alone and (ii) that not all navigational paths are equally useful. Intelligent selection based on path characteristics can improve accuracy. The authors’ work makes an argument for expanding the existing arsenal of data sources for calculating semantic relatedness and to consider the utility of human navigational paths for this task.}, author = {Singer, Philipp and Niebler, Thomas and Strohmaier, Markus and Hotho, Andreas}, journal = {IJSWIS}, keywords = {wikipedia}, number = 4, pages = {41–70}, publisher = {IGI Global}, title = {Computing Semantic Relatedness from Human Navigational Paths: A Case Study on Wikipedia}, volume = 9, year = 2013 }
• 
  Explanation in Episodic and Continuous Decision Support Systems Baumeister, Joachim; Striffler, Albrecht in FGWM’13: Proceedings of German Workshop of Knowledge and Experience Management (at LWA’2013) (2013).
  • [ Abstract ]
  • [ BibTeX ]
  Advanced decision support systems demand for their episodic and collaborative use in order to solve complex problems. Further, continuous knowledge representations help to build large knowledge spaces. Decision support systems enhanced in these ways, however, require new approaches to explain the derived decisions. In this paper, we propose an explanation approach that is based on the standardized PROV ontology. We discuss its applicability by giving practical examples.

  @inproceedings{BSLWA:13, abstract = {Advanced decision support systems demand for their episodic and collaborative use in order to solve complex problems. Further, continuous knowledge representations help to build large knowledge spaces. Decision support systems enhanced in these ways, however, require new approaches to explain the derived decisions. In this paper, we propose an explanation approach that is based on the standardized PROV ontology. We discuss its applicability by giving practical examples.}, author = {Baumeister, Joachim and Striffler, Albrecht}, booktitle = {FGWM'13: Proceedings of German Workshop of Knowledge and Experience Management (at LWA'2013)}, keywords = {myown}, title = {Explanation in Episodic and Continuous Decision Support Systems}, year = 2013 }
• 
  Implementierung einer HTML5-Applikation mit Offline-Fähigkeit zur Erstellung von Graphen für den Einsatz im CaseTrain-Projekt Krebs, Jonathan (2013).
  • [ BibTeX ]
  @mastersthesis{krebs2013implementierung, author = {Krebs, Jonathan}, keywords = {myown}, title = {Implementierung einer HTML5-Applikation mit Offline-Fähigkeit zur Erstellung von Graphen für den Einsatz im CaseTrain-Projekt}, year = 2013 }
• 
  Difference-Based Estimates for Generalization-Aware Subgroup Discovery. Lemmerich, Florian; Becker, Martin; Puppe, Frank in ECML/PKDD (3), Lecture Notes in Computer Science, H. Blockeel, K. Kersting, S. Nijssen, F. Zelezný (eds.) (2013). (Vol. 8190) 288–303.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{conf/pkdd/Lemmerich0P13, author = {Lemmerich, Florian and Becker, Martin and Puppe, Frank}, booktitle = {ECML/PKDD (3)}, crossref = {conf/pkdd/2013-3}, editor = {Blockeel, Hendrik and Kersting, Kristian and Nijssen, Siegfried and Zelezný, Filip}, keywords = {subgroup}, pages = {288-303}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Difference-Based Estimates for Generalization-Aware Subgroup Discovery.}, volume = 8190, year = 2013 }
• 
  ADIA: A Novel Onboard Failure Diagnostic System for Nanosatellites Fellinger, Gerhard; Dietrich, Georg; Fette, Georg; Kayal, Hakan; Puppe, Frank; Schneider, Volker; Wojtkowiak, Harald in 64th International Astronautical Congress (2013). (Vol. 4, 3)
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  Spacecraft failure analysis is often a time-consuming process which requires increased attention from ground personnel. Since operations expenditures represent a major part of overall satellite mission cost, efficient assignment of resources, especially when it comes to as weighty a cost factor as manpower, is critical. This is especially true for small-scale satellites which are often operated by research groups with limited means. Also, ground-based error source isolation by operators implies that due to limited contact windows, real-time diagnosis is usually out of the question, hence losing valuable time when quick reactions to critical failures are necessary. Moreover, the onset of failures looming for several days or weeks cannot be easily predicted by human operators who are by and large not good at trend-analyzing large amounts of data, especially if mutually interdependent time series are involved. Thus, the capability to analyze errors in real-time onboard a satellite is desirable as it can help cut costs and reduce mission failure risk. In order to provide such capabilities, the development of a new autonomous failure diagnostic system called ADIA (Autonomous Diagnostic System for Satellites) has started at the University of Würzburg which is funded through the German Aerospace Center (FKZ 50RM1231) by the Federal Ministry of Economics and Technology (BMWi). The goal is to develop an onboard diagnostic software which is capable of detecting errors, isolating them with respect to their cause as well as trend analysis of spacecraft telemetry data for the prediction of future subsystem malfunctions. The system consists of two functionally intertwined components. One is a set of diagnostic algorithms with an interface to the satellite’s TTC system. The second is a satellite simulator software which has two functions: on the one hand, it serves as a “telemetry generator” in the context of ADIA’s development process, providing the diagnostic core with raw data during system testing and fine-tuning. On the other hand, the simulator can itself be integrated into the diagnostic component, thus making ADIA a model-based analysis tool. Internal states of the simulator can be compared with the state of the actual satellite in order to derive hypotheses on the nature of an emerging error. The focus of this paper lies on the discussion of ADIA’s requirements, the basic functional concept as well as the workings of the diagnostic core. Additionally, a brief discussion of the nanosatellite to be modeled as part of the development process is included.

  @inproceedings{fellinger2013novel, abstract = {Spacecraft failure analysis is often a time-consuming process which requires increased attention from ground personnel. Since operations expenditures represent a major part of overall satellite mission cost, efficient assignment of resources, especially when it comes to as weighty a cost factor as manpower, is critical. This is especially true for small-scale satellites which are often operated by research groups with limited means. Also, ground-based error source isolation by operators implies that due to limited contact windows, real-time diagnosis is usually out of the question, hence losing valuable time when quick reactions to critical failures are necessary. Moreover, the onset of failures looming for several days or weeks cannot be easily predicted by human operators who are by and large not good at trend-analyzing large amounts of data, especially if mutually interdependent time series are involved. Thus, the capability to analyze errors in real-time onboard a satellite is desirable as it can help cut costs and reduce mission failure risk. In order to provide such capabilities, the development of a new autonomous failure diagnostic system called ADIA (Autonomous Diagnostic System for Satellites) has started at the University of Würzburg which is funded through the German Aerospace Center (FKZ 50RM1231) by the Federal Ministry of Economics and Technology (BMWi). The goal is to develop an onboard diagnostic software which is capable of detecting errors, isolating them with respect to their cause as well as trend analysis of spacecraft telemetry data for the prediction of future subsystem malfunctions. The system consists of two functionally intertwined components. One is a set of diagnostic algorithms with an interface to the satellite’s TTC system. The second is a satellite simulator software which has two functions: on the one hand, it serves as a “telemetry generator” in the context of ADIA’s development process, providing the diagnostic core with raw data during system testing and fine-tuning. On the other hand, the simulator can itself be integrated into the diagnostic component, thus making ADIA a model-based analysis tool. Internal states of the simulator can be compared with the state of the actual satellite in order to derive hypotheses on the nature of an emerging error. The focus of this paper lies on the discussion of ADIA’s requirements, the basic functional concept as well as the workings of the diagnostic core. Additionally, a brief discussion of the nanosatellite to be modeled as part of the development process is included.}, author = {Fellinger, Gerhard and Dietrich, Georg and Fette, Georg and Kayal, Hakan and Puppe, Frank and Schneider, Volker and Wojtkowiak, Harald}, booktitle = {64th International Astronautical Congress}, keywords = {myown}, organization = {International Astronautical Federation}, title = {ADIA: A Novel Onboard Failure Diagnostic System for Nanosatellites}, volume = {IAC-13,B4,3,10,x17926}, year = 2013 }
• 
  Constraint-driven Evaluation in UIMA Ruta. Wittek, Andreas; Toepfer, Martin; Fette, Georg; Klügl, Peter; Puppe, Frank in UIMA@GSCL, CEUR Workshop Proceedings, P. Klügl, R. Eckart de Castilho, K. Tomanek (eds.) (2013). (Vol. 1038) 58–65.
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  @inproceedings{conf/gldv/WittekTFKP13, author = {Wittek, Andreas and Toepfer, Martin and Fette, Georg and Klügl, Peter and Puppe, Frank}, booktitle = {UIMA@GSCL}, crossref = {conf/gldv/2013uima}, editor = {Klügl, Peter and Eckart de Castilho, Richard and Tomanek, Katrin}, keywords = {uima}, pages = {58-65}, publisher = {CEUR-WS.org}, series = {CEUR Workshop Proceedings}, title = {Constraint-driven Evaluation in UIMA Ruta.}, volume = 1038, year = 2013 }
• 
  Storing UIMA CASes in a relational database. Fette, Georg; Toepfer, Martin; Puppe, Frank in UIMA@GSCL, CEUR Workshop Proceedings, P. Klügl, R. E. de Castilho, K. Tomanek (eds.) (2013). (Vol. 1038) 10–13.
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  @inproceedings{conf/gldv/FetteTP13, author = {Fette, Georg and Toepfer, Martin and Puppe, Frank}, booktitle = {UIMA@GSCL}, crossref = {conf/gldv/2013uima}, editor = {Klügl, Peter and de Castilho, Richard Eckart and Tomanek, Katrin}, keywords = {myown}, pages = {10-13}, publisher = {CEUR-WS.org}, series = {CEUR Workshop Proceedings}, title = {Storing UIMA CASes in a relational database.}, volume = 1038, year = 2013 }
• 
  {Exploratory Pattern Mining on Social Media using Geo-References and Social Tagging Information} Atzmueller, Martin; Lemmerich, Florian in International Journal of Web Science (Special Issue on Social Web Search and Mining) (2013).
  • [ BibTeX ]
  @article{AL:13, author = {Atzmueller, Martin and Lemmerich, Florian}, journal = {International Journal of Web Science (Special Issue on Social Web Search and Mining)}, keywords = {myown}, title = {{Exploratory Pattern Mining on Social Media using Geo-References and Social Tagging Information}}, year = 2013 }
• 
  Towards Continuous Knowledge Representations in Episodic and Collaborative Decision Making Baumeister, Joachim; Striffler, Albrecht; Brandt, Marc; Neumann, Michael in The 9th Workshop on Knowledge Engineering and Software Engineering (KESE2013) (2013). (Vol. CEUR Proceedings Vol-1070)
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  With the success of knowledge-based approaches in decision support systems new requirements arise in practice. That way, users demand not only for the collaborative development of such systems, but also for the collaborative and episodic use in decision processes. Moreover, in complex decision domains multiple knowledge representations are available that need to be jointly processed. In this paper we introduce a novel approach and a system implementation that aims to meet these requirements.

  @inproceedings{BSBN:13, abstract = {With the success of knowledge-based approaches in decision support systems new requirements arise in practice. That way, users demand not only for the collaborative development of such systems, but also for the collaborative and episodic use in decision processes. Moreover, in complex decision domains multiple knowledge representations are available that need to be jointly processed. In this paper we introduce a novel approach and a system implementation that aims to meet these requirements.}, author = {Baumeister, Joachim and Striffler, Albrecht and Brandt, Marc and Neumann, Michael}, booktitle = {The 9th Workshop on Knowledge Engineering and Software Engineering (KESE2013)}, keywords = {wiki}, title = {Towards Continuous Knowledge Representations in Episodic and Collaborative Decision Making}, volume = {CEUR Proceedings Vol-1070}, year = 2013 }
• 
  Towards the Semantification of Technical Documents Furth, Sebastian; Baumeister, Joachim in FGIR’13: Proceedings of German Workshop of Information Retrieval (at LWA’2013) (2013).
  • [ Abstract ]
  • [ BibTeX ]
  In the domain of engineering large corpora of technical documents are commonly created and used. Applications such as semantic search offer advantages in accessing those documents, but require them to be semantically annotated. Annotating these corpora manually is in most cases not feasible. In recent years a lot of machine learning methods have proved their ability to annotate documents automatically. The down-side of these methods is their need for training data. We present a holistic approach for the semantification of technical documents without training data. The approach tackles different challenges such as terminology extraction, semantic annotation, and reviewing. Our approach has been successfully applied to the technical documents corpora of two German machine builders

  @inproceedings{FBLWA:13, abstract = {In the domain of engineering large corpora of technical documents are commonly created and used. Applications such as semantic search offer advantages in accessing those documents, but require them to be semantically annotated. Annotating these corpora manually is in most cases not feasible. In recent years a lot of machine learning methods have proved their ability to annotate documents automatically. The down-side of these methods is their need for training data. We present a holistic approach for the semantification of technical documents without training data. The approach tackles different challenges such as terminology extraction, semantic annotation, and reviewing. Our approach has been successfully applied to the technical documents corpora of two German machine builders}, author = {Furth, Sebastian and Baumeister, Joachim}, booktitle = {FGIR'13: Proceedings of German Workshop of Information Retrieval (at LWA'2013)}, keywords = {myown}, title = {Towards the Semantification of Technical Documents}, year = 2013 }
• 
  {Wissensmodellierung und Visualisierung in der Kataraktchirurgie} Scherer, Klaus-Peter; Rieder, Constantin; Henninger, Christian; Baumeister, Joachim; Reutelshöfer, Jochen in Spektrum Augenheilkunde (2013). 27 109.
  • [ BibTeX ]
  @article{scherer2013wissensmodellierung, author = {Scherer, Klaus-Peter and Rieder, Constantin and Henninger, Christian and Baumeister, Joachim and Reutelshöfer, Jochen}, journal = {Spektrum Augenheilkunde}, keywords = {wissass}, pages = 109, publisher = {Springer}, title = {{Wissensmodellierung und Visualisierung in der Kataraktchirurgie}}, volume = 27, year = 2013 }
• 
  New Concepts for Knowledge Based Cataract Surgery Assistance Scherer, Klaus-Peter; Rieder, Constantin; Henninger, Christian; Baumeister, Joachim; Reutelshöfer, Jochen in Proc. of the 8th International Joint Conference on Software Technologies (2013).
  • [ BibTeX ]
  @inproceedings{scherer2013concepts, author = {Scherer, Klaus-Peter and Rieder, Constantin and Henninger, Christian and Baumeister, Joachim and Reutelshöfer, Jochen}, booktitle = {Proc. of the 8th International Joint Conference on Software Technologies}, keywords = {wiki}, month = {July}, title = {New Concepts for Knowledge Based Cataract Surgery Assistance}, year = 2013 }
• 
  How Tagging Pragmatics Influence Tag Sense Discovery in Social Annotation Systems Niebler, Thomas; Singer, Philipp; Benz, Dominik; Körner, Christian; Strohmaier, Markus; Hotho, Andreas in ECIR (2013). 86–97.
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  The presence of emergent semantics in social annotation systems has been reported in numerous studies. Two important problems in this context are the induction of semantic relations among tags and the discovery of different senses of a given tag. While a number of approaches for discovering tag senses exist, little is known about which

  @inproceedings{niebler2013tagging, abstract = {The presence of emergent semantics in social annotation systems has been reported in numerous studies. Two important problems in this context are the induction of semantic relations among tags and the discovery of different senses of a given tag. While a number of approaches for discovering tag senses exist, little is known about which}, author = {Niebler, Thomas and Singer, Philipp and Benz, Dominik and Körner, Christian and Strohmaier, Markus and Hotho, Andreas}, booktitle = {ECIR}, keywords = {tau}, pages = {86-97}, publisher = {Springer}, title = {How Tagging Pragmatics Influence Tag Sense Discovery in Social Annotation Systems}, year = 2013 }
• 
  Exploiting Structural Consistencies with Stacked Conditional Random Fields Kluegl, Peter; Toepfer, Martin; Lemmerich, Florian; Hotho, Andreas; Puppe, Frank in Mathematical Methodologies in Pattern Recognition and Machine Learning Springer Proceedings in Mathematics & Statistics (2013). 30 111–125.
  • [ Abstract ]
  • [ BibTeX ]
  Conditional Random Fields (CRF) are popular methods for labeling unstructured or textual data. Like many machine learning approaches, these undirected graphical models assume the instances to be independently distributed. However, in real-world applications data is grouped in a natural way, e.g., by its creation context. The instances in each group often share additional structural consistencies. This paper proposes a domain-independent method for exploiting these consistencies by combining two CRFs in a stacked learning framework. We apply rule learning collectively on the predictions of an initial CRF for one context to acquire descriptions of its specific properties. Then, we utilize these descriptions as dynamic and high quality features in an additional (stacked) CRF. The presented approach is evaluated with a real-world dataset for the segmentation of references and achieves a significant reduction of the labeling error.

  @article{kluegl2013exploiting, abstract = {Conditional Random Fields (CRF) are popular methods for labeling unstructured or textual data. Like many machine learning approaches, these undirected graphical models assume the instances to be independently distributed. However, in real-world applications data is grouped in a natural way, e.g., by its creation context. The instances in each group often share additional structural consistencies. This paper proposes a domain-independent method for exploiting these consistencies by combining two CRFs in a stacked learning framework. We apply rule learning collectively on the predictions of an initial CRF for one context to acquire descriptions of its specific properties. Then, we utilize these descriptions as dynamic and high quality features in an additional (stacked) CRF. The presented approach is evaluated with a real-world dataset for the segmentation of references and achieves a significant reduction of the labeling error.}, author = {Kluegl, Peter and Toepfer, Martin and Lemmerich, Florian and Hotho, Andreas and Puppe, Frank}, journal = {Mathematical Methodologies in Pattern Recognition and Machine Learning Springer Proceedings in Mathematics & Statistics}, keywords = {structural}, pages = {111-125}, title = {Exploiting Structural Consistencies with Stacked Conditional Random Fields}, volume = 30, year = 2013 }
• 
  Supporting Direct Knowledge Acquisition by Customized Tools: A Case Study in the Domain of Cataract Surgery Reutelsh{\"o}fer, Jochen; Baumeister, Joachim in FGWM’13: Proceedings of German Workshop of Knowledge and Experience Management (at LWA’2013) (2013).
  • [ BibTeX ]
  @inproceedings{RBLWA:13, author = {Reutelsh{\"o}fer, Jochen and Baumeister, Joachim}, booktitle = {FGWM'13: Proceedings of German Workshop of Knowledge and Experience Management (at LWA'2013)}, keywords = {myown}, title = {Supporting Direct Knowledge Acquisition by Customized Tools: A Case Study in the Domain of Cataract Surgery}, year = 2013 }
• 
  {Prototyping-based Usability-oriented Knowledge Systems Engineering} Freiberg, Martina; Puppe, Frank in {Mensch und Computer 2012---12. fach{\"u}bergreifende Konferenz für interaktive und kooperative Medien.}, H. Reiterer, O. Deussen (eds.) (2013).
  • [ BibTeX ]
  @inproceedings{Freiberg2013a, author = {Freiberg, Martina and Puppe, Frank}, booktitle = {{Mensch und Computer 2012—12. fach{\"u}bergreifende Konferenz für interaktive und kooperative Medien.}}, editor = {Reiterer, Harald and Deussen, Oliver}, keywords = {myown}, publisher = {Oldenbourg Verlag}, title = {{Prototyping-based Usability-oriented Knowledge Systems Engineering}}, year = 2013 }
• 
  Constraint-driven Evaluation in UIMA Ruta. Wittek, Andreas; Toepfer, Martin; Fette, Georg; Klügl, Peter; Puppe, Frank in UIMA@GSCL, CEUR Workshop Proceedings, P. Klügl, R. Eckart de Castilho, K. Tomanek (eds.) (2013). (Vol. 1038) 58–65.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{conf/gldv/WittekTFKP13, author = {Wittek, Andreas and Toepfer, Martin and Fette, Georg and Klügl, Peter and Puppe, Frank}, booktitle = {UIMA@GSCL}, crossref = {conf/gldv/2013uima}, editor = {Klügl, Peter and Eckart de Castilho, Richard and Tomanek, Katrin}, keywords = {uima}, pages = {58-65}, publisher = {CEUR-WS.org}, series = {CEUR Workshop Proceedings}, title = {Constraint-driven Evaluation in UIMA Ruta.}, volume = 1038, year = 2013 }
• 
  Computing Semantic Relatedness from Human Navigational Paths on Wikipedia Singer, Philipp; Niebler, Thomas; Strohmaier, Markus; Hotho, Andreas in Proceedings of the 22nd International Conference on World Wide Web, L. Carr, A. H. F. Laender, B. F. Lóscio, I. King, M. Fontoura, D. Vrandecic, L. Aroyo, J. P. M. de Oliveira, F. Lima, E. Wilde (eds.) (2013). 171–172.
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  This paper presents a novel approach for computing semantic relatedness between concepts on Wikipedia by using human navigational paths for this task. Our results suggest that human navigational paths provide a viable source for calculating semantic relatedness between concepts on Wikipedia. We also show that we can improve accuracy by intelligent selection of path corpora based on path characteristics indicating that not all paths are equally useful. Our work makes an argument for expanding the existing arsenal of data sources for calculating semantic relatedness and to consider the utility of human navigational paths for this task.

  @inproceedings{singer2013computing_www, abstract = {This paper presents a novel approach for computing semantic relatedness between concepts on Wikipedia by using human navigational paths for this task. Our results suggest that human navigational paths provide a viable source for calculating semantic relatedness between concepts on Wikipedia. We also show that we can improve accuracy by intelligent selection of path corpora based on path characteristics indicating that not all paths are equally useful. Our work makes an argument for expanding the existing arsenal of data sources for calculating semantic relatedness and to consider the utility of human navigational paths for this task.}, author = {Singer, Philipp and Niebler, Thomas and Strohmaier, Markus and Hotho, Andreas}, booktitle = {Proceedings of the 22nd International Conference on World Wide Web}, editor = {Carr, Leslie and Laender, Alberto H. F. and Lóscio, Bernadette Farias and King, Irwin and Fontoura, Marcus and Vrandecic, Denny and Aroyo, Lora and de Oliveira, José Palazzo M. and Lima, Fernanda and Wilde, Erik}, keywords = {wikipedia}, organization = {ACM}, pages = {171–172}, publisher = {ACM}, title = {Computing Semantic Relatedness from Human Navigational Paths on Wikipedia}, year = 2013 }

• 
  A Meta-Engineering Approach for Customized Document-centered Knowledge Acquisition Reutelshoefer, Jochen; Baumeister, Joachim; Puppe, Frank in Modellierung 2012, E. Sinz (ed.) (2012).
  • [ BibTeX ]
  @inproceedings{reutelshoefer2012metaengineering, address = {Bamberg}, author = {Reutelshoefer, Jochen and Baumeister, Joachim and Puppe, Frank}, booktitle = {Modellierung 2012}, editor = {Sinz, Elmar}, keywords = {rokt}, title = {A Meta-Engineering Approach for Customized Document-centered Knowledge Acquisition}, year = 2012 }
• 
  Implementing an Automated Ventilation Guideline Using the Semantic Wiki KnowWE Hatko, Reinhard; Sch{\"a}dler, Dirk; Mersmann, Stefan; Baumeister, Joachim; Weiler, Norbert; Puppe, Frank in EKAW, Lecture Notes in Computer Science, A. ten Teije, J. V{\"o}lker, S. Handschuh, H. Stuckenschmidt, M. d’Aquin, A. Nikolov, N. Aussenac-Gilles, N. Hernandez (eds.) (2012). (Vol. 7603) 363–372.
  • [ BibTeX ]
  @inproceedings{Hatko2012, author = {Hatko, Reinhard and Sch{\"a}dler, Dirk and Mersmann, Stefan and Baumeister, Joachim and Weiler, Norbert and Puppe, Frank}, booktitle = {EKAW}, crossref = {DBLP:conf/ekaw/2012}, editor = {ten Teije, Annette and V{\"o}lker, Johanna and Handschuh, Siegfried and Stuckenschmidt, Heiner and d'Aquin, Mathieu and Nikolov, Andriy and Aussenac-Gilles, Nathalie and Hernandez, Nathalie}, keywords = {myown}, pages = {363-372}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Implementing an Automated Ventilation Guideline Using the Semantic Wiki KnowWE}, volume = 7603, year = 2012 }
• 
  Diaflux: A Graphical Language for Computer-Interpretable Guidelines Hatko, Reinhard; Baumeister, Joachim; Belli, Volker; Puppe, Frank in Knowledge Representation for Health-Care, D. Riaño, A. ten Teije, S. Miksch (eds.) (2012). (Vol. 6924) 94–107.
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  In this paper, we introduce the formal representation language DiaFlux, that is simple and easy to use on the one hand. On the other hand it allows for the definition of Computer-Interpretable Guidelines (CIGs), that can solve valuable tasks being executed in the clinical context. Further, we describe a wiki-driven development process using the stepwise formalization and allowing for almost self-acquisition by the domain specialists. The applicability of the approach is demonstrated by a protocol for sepsis monitoring and treatment developed by a collaboration of clinicians.

  @incollection{Hatko2012c, abstract = {In this paper, we introduce the formal representation language DiaFlux, that is simple and easy to use on the one hand. On the other hand it allows for the definition of Computer-Interpretable Guidelines (CIGs), that can solve valuable tasks being executed in the clinical context. Further, we describe a wiki-driven development process using the stepwise formalization and allowing for almost self-acquisition by the domain specialists. The applicability of the approach is demonstrated by a protocol for sepsis monitoring and treatment developed by a collaboration of clinicians.}, address = {Berlin / Heidelberg}, author = {Hatko, Reinhard and Baumeister, Joachim and Belli, Volker and Puppe, Frank}, booktitle = {Knowledge Representation for Health-Care}, editor = {Riaño, David and ten Teije, Annette and Miksch, Silvia}, keywords = {myown}, pages = {94-107}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Diaflux: A Graphical Language for Computer-Interpretable Guidelines}, volume = 6924, year = 2012 }
• 
  Implementing an Automated Ventilation Guideline using the Semantic Wiki {KnowWE} Hatko, Reinhard; Schädler, Dirk; Mersmann, Stefan; Baumeister, Joachim; Weiler, Norbert; Puppe, Frank in EKAW 2012: 18th International Conference on Knowledge Engineering and Knowledge Management, H. Stuckenschmidt, A. ten Teije, J. Voelker (eds.) (2012).
  • [ BibTeX ]
  @inproceedings{hatko2012implementing, author = {Hatko, Reinhard and Schädler, Dirk and Mersmann, Stefan and Baumeister, Joachim and Weiler, Norbert and Puppe, Frank}, booktitle = {EKAW 2012: 18th International Conference on Knowledge Engineering and Knowledge Management}, editor = {Stuckenschmidt, Heiner and ten Teije, Annette and Voelker, Johanna}, keywords = {wiki}, title = {Implementing an Automated Ventilation Guideline using the Semantic Wiki {KnowWE}}, year = 2012 }
• 
  {iTree: Skill-building User-centered Clarification Consultation Interfaces} Freiberg, Martina; Puppe, Frank in {Proceedings of the International Conference on Knowledge Engineering and Ontology Development (KEOD 2012)} (2012).
  • [ BibTeX ]
  @inproceedings{Freiberg2012d, author = {Freiberg, Martina and Puppe, Frank}, booktitle = {{Proceedings of the International Conference on Knowledge Engineering and Ontology Development (KEOD 2012)}}, keywords = {myown}, publisher = {SciTePress Digital Library}, title = {{iTree: Skill-building User-centered Clarification Consultation Interfaces}}, year = 2012 }
• 
  {DiaFlux}: A Graphical Language for Computer-Interpretable Guidelines Hatko, Reinhard; Baumeister, Joachim; Belli, Volker; Puppe, Frank in Knowledge Representation for Health-Care, D. Riaño, A. ten Teije, S. Miksch (eds.) (2012). (Vol. 6924) 94–107.
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  In this paper, we introduce the formal representation language DiaFlux, that is simple and easy to use on the one hand. On the other hand it allows for the definition of Computer-Interpretable Guidelines (CIGs), that can solve valuable tasks being executed in the clinical context. Further, we describe a wiki-driven development process using the stepwise formalization and allowing for almost self-acquisition by the domain specialists. The applicability of the approach is demonstrated by a protocol for sepsis monitoring and treatment developed by a collaboration of clinicians.

  @incollection{springerlink:10.1007/978-3-642-27697-2_7, abstract = {In this paper, we introduce the formal representation language DiaFlux, that is simple and easy to use on the one hand. On the other hand it allows for the definition of Computer-Interpretable Guidelines (CIGs), that can solve valuable tasks being executed in the clinical context. Further, we describe a wiki-driven development process using the stepwise formalization and allowing for almost self-acquisition by the domain specialists. The applicability of the approach is demonstrated by a protocol for sepsis monitoring and treatment developed by a collaboration of clinicians.}, address = {Berlin / Heidelberg}, author = {Hatko, Reinhard and Baumeister, Joachim and Belli, Volker and Puppe, Frank}, booktitle = {Knowledge Representation for Health-Care}, editor = {Riaño, David and ten Teije, Annette and Miksch, Silvia}, keywords = {rokt}, pages = {94-107}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {{DiaFlux}: A Graphical Language for Computer-Interpretable Guidelines}, volume = 6924, year = 2012 }
• 
  Stacked Conditional Random Fields Exploiting Structural Consistencies Kluegl, Peter; Toepfer, Martin; Lemmerich, Florian; Hotho, Andreas; Puppe, Frank in Proceedings of 1st International Conference on Pattern Recognition Applications and Methods (ICPRAM), P. L. Carmona, J. S. Sánchez, A. Fred (eds.) (2012). 240–248.
  • [ Abstract ]
  • [ BibTeX ]
  • [ URL ]
  Conditional Random Fields (CRF) are popular methods for labeling unstructured or textual data. Like many machine learning approaches these undirected graphical models assume the instances to be independently distributed. However, in real world applications data is grouped in a natural way, e.g., by its creation context. The instances in each group often share additional structural consistencies. This paper proposes a domain-independent method for exploiting these consistencies by combining two CRFs in a stacked learning framework. The approach incorporates three successive steps of inference: First, an initial CRF processes single instances as usual. Next, we apply rule learning collectively on all labeled outputs of one context to acquire descriptions of its specific properties. Finally, we utilize these descriptions as dynamic and high quality features in an additional (stacked) CRF. The presented approach is evaluated with a real-world dataset for the segmentation of references and achieves a significant reduction of the labeling error.

  @inproceedings{kluegl2012stacked, abstract = {Conditional Random Fields (CRF) are popular methods for labeling unstructured or textual data. Like many machine learning approaches these undirected graphical models assume the instances to be independently distributed. However, in real world applications data is grouped in a natural way, e.g., by its creation context. The instances in each group often share additional structural consistencies. This paper proposes a domain-independent method for exploiting these consistencies by combining two CRFs in a stacked learning framework. The approach incorporates three successive steps of inference: First, an initial CRF processes single instances as usual. Next, we apply rule learning collectively on all labeled outputs of one context to acquire descriptions of its specific properties. Finally, we utilize these descriptions as dynamic and high quality features in an additional (stacked) CRF. The presented approach is evaluated with a real-world dataset for the segmentation of references and achieves a significant reduction of the labeling error.}, address = {Vilamoura, Algarve, Portugal}, author = {Kluegl, Peter and Toepfer, Martin and Lemmerich, Florian and Hotho, Andreas and Puppe, Frank}, booktitle = {Proceedings of 1st International Conference on Pattern Recognition Applications and Methods (ICPRAM)}, editor = {Carmona, Pedro Latorre and Sánchez, J. Salvador and Fred, Ana}, keywords = {structural}, month = {February}, pages = {240-248}, publisher = {SciTePress}, title = {Stacked Conditional Random Fields Exploiting Structural Consistencies}, year = 2012 }
• 
  Collective Information Extraction with Context-Specific Consistencies. Klügl, Peter; Toepfer, Martin; Lemmerich, Florian; Hotho, Andreas; Puppe, Frank in ECML/PKDD (1), Lecture Notes in Computer Science, P. A. Flach, T. D. Bie, N. Cristianini (eds.) (2012). (Vol. 7523) 728–743.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{conf/pkdd/KluglTLHP12, author = {Klügl, Peter and Toepfer, Martin and Lemmerich, Florian and Hotho, Andreas and Puppe, Frank}, booktitle = {ECML/PKDD (1)}, crossref = {conf/pkdd/2012-1}, editor = {Flach, Peter A. and Bie, Tijl De and Cristianini, Nello}, keywords = {text}, pages = {728-743}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Collective Information Extraction with Context-Specific Consistencies.}, volume = 7523, year = 2012 }
• 
  {Extensible Prototyping for Pragmatic Engineering of Knowledge-based Systems} Freiberg, Martina; Striffler, Albrecht; Puppe, Frank in Expert Systems with Applications (2012). doi: 10.1016/j.eswa.2012.02.110
  • [ BibTeX ]
  @article{Freiberg2012, author = {Freiberg, Martina and Striffler, Albrecht and Puppe, Frank}, journal = {Expert Systems with Applications}, keywords = {usability}, title = {{Extensible Prototyping for Pragmatic Engineering of Knowledge-based Systems}}, volume = {doi: 10.1016/j.eswa.2012.02.110}, year = 2012 }
• 
  {iTree: Skill-building User-centered Clarification Consultation Interfaces (Resubmission of KEOD 2012 article} Freiberg, Martina; Puppe, Frank in LWA-2012 (Special Track on Knowledge Management) (2012).
  • [ BibTeX ]
  @inproceedings{Freiberg2012c, author = {Freiberg, Martina and Puppe, Frank}, booktitle = {LWA-2012 (Special Track on Knowledge Management)}, keywords = {myown}, title = {{iTree: Skill-building User-centered Clarification Consultation Interfaces (Resubmission of KEOD 2012 article}}, year = 2012 }
• 
  A Document-Centered Authoring Approach for Ontology Engineering Reutelshoefer, Jochen; Baumeister, Joachim; Fette, Georg; Puppe, Frank in FGWM’12: Proceedings of German Workshop of Knowledge and Experience Management (at LWA’2012), (LWA2012, ed.) (2012).
  • [ BibTeX ]
  @article{noauthororeditor2012documentcentered, author = {Reutelshoefer, Jochen and Baumeister, Joachim and Fette, Georg and Puppe, Frank}, editor = {LWA2012}, journal = {FGWM'12: Proceedings of German Workshop of Knowledge and Experience Management (at LWA'2012)}, keywords = {myown}, title = {A Document-Centered Authoring Approach for Ontology Engineering}, year = 2012 }
• 
  Information Extraction from Unstructured Electronic Health Records and Integration into a Data Warehouse. Fette, Georg; Ertl, Maximilian; Wörner, Anja; Klügl, Peter; Störk, Stefan; Puppe, Frank in GI-Jahrestagung, LNI, U. Goltz, M. A. Magnor, H.-J. Appelrath, H. K. Matthies, W.-T. Balke, L. C. Wolf (eds.) (2012). (Vol. 208) 1237–1251.
  • [ BibTeX ]
  • [ URL ]
  • [ Download ]
  @inproceedings{conf/gi/FetteEWKSP12, author = {Fette, Georg and Ertl, Maximilian and Wörner, Anja and Klügl, Peter and Störk, Stefan and Puppe, Frank}, booktitle = {GI-Jahrestagung}, crossref = {conf/gi/2012}, editor = {Goltz, Ursula and Magnor, Marcus A. and Appelrath, Hans-Jürgen and Matthies, Herbert K. and Balke, Wolf-Tilo and Wolf, Lars C.}, keywords = {myown}, pages = {1237-1251}, publisher = {GI}, series = {LNI}, title = {Information Extraction from Unstructured Electronic Health Records and Integration into a Data Warehouse.}, volume = 208, year = 2012 }
• 
  {Template-based Extensible Prototyping for Creativity- and Usability-Oriented Knowledge Systems Development} Freiberg, Martina; Puppe, Frank in {Proceedings of the 8th Workshop on Knowledge Engineering and Software Engineering (KESE8)}, {Grzegorz J. Nalepa, Joaqu\’{i}n Ca\~{n}adas, Joachim Baumeister} (eds.) (2012).
  • [ BibTeX ]
  @inproceedings{freiberg2012templatebased, author = {Freiberg, Martina and Puppe, Frank}, booktitle = {{Proceedings of the 8th Workshop on Knowledge Engineering and Software Engineering (KESE8)}}, editor = {{Grzegorz J. Nalepa and Joaqu\'{i}n Ca\ {n}adas and Joachim Baumeister}}, keywords = {usability}, publisher = {CEUR Proceedings (to appear)}, title = {{Template-based Extensible Prototyping for Creativity- and Usability-Oriented Knowledge Systems Development}}, year = 2012 }
• 
  Collective Information Extraction with Context-Specific Consistencies. Klügl, Peter; Toepfer, Martin; Lemmerich, Florian; Hotho, Andreas; Puppe, Frank in ECML/PKDD (1), Lecture Notes in Computer Science, P. A. Flach, T. D. Bie, N. Cristianini (eds.) (2012). (Vol. 7523) 728–743.
  • [ BibTeX ]
  • [ URL ]
  @inproceedings{conf/pkdd/KluglTLHP12, author = {Klügl, Peter and Toepfer, Martin and Lemmerich, Florian and Hotho, Andreas and Puppe, Frank}, booktitle = {ECML/PKDD (1)}, crossref = {conf/pkdd/2012-1}, editor = {Flach, Peter A. and Bie, Tijl De and Cristianini, Nello}, keywords = {text}, pages = {728-743}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Collective Information Extraction with Context-Specific Consistencies.}, volume = 7523, year = 2012 }
• 
  Simulation-based Test Case Generation for Clinical Guidelines Hatko, Reinhard; Lemmerich, Florian; Baumeister, Joachim; Puppe, Frank in In the Proceedings of the 5th International Workshop on Process-oriented Information Systems in Healthcare / 4th International Workshop on Knowledge Representation for Health Care (2012).
  • [ BibTeX ]
  @inproceedings{Hatko2012a, author = {Hatko, Reinhard and L