Toepfer, Martin

2015 [ nach oben ]

• Toepfer, M., Corovic, H., Fette, G., Klügl, P., Störk, S., Puppe, F.: Fine-grained information extraction from German transthoracic echocardiography reports. BMC Medical Informatics and Decision Making. 15, 103 (2015).
  [ BibTeX ] [ EndNote ] [ 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 }
  %0 Journal Article %1 Toepfer2015 %A Toepfer, Martin %A Corovic, Hamo %A Fette, Georg %A Klügl, Peter %A Störk, Stefan %A Puppe, Frank %D 2015 %J BMC Medical Informatics and Decision Making %P 103 %R 10.1186/s12911-015-0215-x %T Fine-grained information extraction from German transthoracic echocardiography reports %U http://dx.doi.org/10.1186/s12911-015-0215-x %V 15

2014 [ nach oben ]

• Toepfer, M., Fette, G., Beck, P.-D., Klügl, P., Puppe, F.: Integrated Tools for Query-driven Development of Light-weight Ontologies and Information Extraction Components. Proceedings of the Workshop on Open Infrastructures and Analysis Frameworks for HLT. p. 83--92. , Dublin, Ireland (2014).
  [ BibTeX ] [ EndNote ]
   
  @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 }
  %0 Conference Paper %1 Toepfer2014 %A Toepfer, Martin %A Fette, Georg %A Beck, Philip-Daniel %A Klügl, Peter %A Puppe, Frank %B Proceedings of the Workshop on Open Infrastructures and Analysis Frameworks for HLT %C Dublin, Ireland %D 2014 %P 83--92 %T Integrated Tools for Query-driven Development of Light-weight Ontologies and Information Extraction Components

2012 [ nach oben ]

• Klügl, P., Toepfer, M., Lemmerich, F., Hotho, A., Puppe, F.: Collective Information Extraction with Context-Specific Consistencies. In: Flach, P.A., Bie, T.D., and Cristianini, N. (eds.) ECML/PKDD (1). pp. 728-743. Springer (2012).
  [ BibTeX ] [ EndNote ] [ 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 = {myown}, pages = {728-743}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Collective Information Extraction with Context-Specific Consistencies.}, volume = 7523, year = 2012 }
  %0 Conference Paper %1 conf/pkdd/KluglTLHP12 %A Klügl, Peter %A Toepfer, Martin %A Lemmerich, Florian %A Hotho, Andreas %A Puppe, Frank %B ECML/PKDD (1) %D 2012 %E Flach, Peter A. %E Bie, Tijl De %E Cristianini, Nello %I Springer %P 728-743 %T Collective Information Extraction with Context-Specific Consistencies. %U http://dblp.uni-trier.de/db/conf/pkdd/pkdd2012-1.html#KluglTLHP12 %V 7523 %@ 978-3-642-33459-7
• Kluegl, P., Toepfer, M., Lemmerich, F., Hotho, A., Puppe, F.: Stacked Conditional Random Fields Exploiting Structural Consistencies. In: Carmona, P.L., Sánchez, J.S., and Fred, A. (eds.) Proceedings of 1st International Conference on Pattern Recognition Applications and Methods (ICPRAM). pp. 240-248. SciTePress, Vilamoura, Algarve, Portugal (2012).
  [ Abstract ] [ BibTeX ] [ EndNote ] [ 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 = {myown}, month = {February}, pages = {240-248}, publisher = {SciTePress}, title = {Stacked Conditional Random Fields Exploiting Structural Consistencies}, year = 2012 }
  %0 Conference Paper %1 kluegl2012stacked %A Kluegl, Peter %A Toepfer, Martin %A Lemmerich, Florian %A Hotho, Andreas %A Puppe, Frank %B Proceedings of 1st International Conference on Pattern Recognition Applications and Methods (ICPRAM) %C Vilamoura, Algarve, Portugal %D 2012 %E Carmona, Pedro Latorre %E Sánchez, J. Salvador %E Fred, Ana %I SciTePress %P 240-248 %T Stacked Conditional Random Fields Exploiting Structural Consistencies %U http://ki.informatik.uni-wuerzburg.de/papers/pkluegl/2012-ICPRAM-StackedCRF.pdf %X 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.

2010 [ nach oben ]

• Toepfer, M., Kluegl, P., Hotho, A., Puppe., F.: Conditional Random Fields For Local Adaptive Reference Extraction. In: Atzmüller, M., Benz, D., Hotho, A., and Stumme, G. (eds.) Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen & Adaptivitaet. , Kassel, Germany (2010).
  [ Abstract ] [ BibTeX ] [ EndNote ] [ URL ]
   
  The accurate extraction of bibliographic information from scientific publications is an active field of research. Machine learning and sequence labeling approaches like Conditional Random Fields (CRF) are often applied for this reference extraction task, but still suffer from the ambiguity of reference notation. Reference sections apply a predefined style guide and contain only homogeneous references. Therefore, other references of the same paper or journal often provide evidence how the fields of a reference are correctly labeled. We propose a novel approach that exploits the similarities within a document. Our process model uses information of unlabeled documents directly during the extraction task in order to automatically adapt to the perceived style guide. This is implemented by changing the manifestation of the features for the applied CRF. The experimental results show considerable improvements compared to the common approach. We achieve an average F1 score of 96.7% and an instance accuracy of 85.4% on the test data set.
  @inproceedings{kdml21, abstract = {The accurate extraction of bibliographic information from scientific publications is an active field of research. Machine learning and sequence labeling approaches like Conditional Random Fields (CRF) are often applied for this reference extraction task, but still suffer from the ambiguity of reference notation. Reference sections apply a predefined style guide and contain only homogeneous references. Therefore, other references of the same paper or journal often provide evidence how the fields of a reference are correctly labeled. We propose a novel approach that exploits the similarities within a document. Our process model uses information of unlabeled documents directly during the extraction task in order to automatically adapt to the perceived style guide. This is implemented by changing the manifestation of the features for the applied CRF. The experimental results show considerable improvements compared to the common approach. We achieve an average F1 score of 96.7% and an instance accuracy of 85.4% on the test data set.}, address = {Kassel, Germany}, author = {Toepfer, Martin and Kluegl, Peter and Hotho, Andreas and Puppe., Frank}, booktitle = {Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen {\&} Adaptivitaet}, crossref = {lwa2010}, editor = {Atzmüller, Martin and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, keywords = {myown}, title = {Conditional Random Fields For Local Adaptive Reference Extraction}, year = 2010 }
  %0 Conference Paper %1 kdml21 %A Toepfer, Martin %A Kluegl, Peter %A Hotho, Andreas %A Puppe., Frank %B Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen & Adaptivitaet %C Kassel, Germany %D 2010 %E Atzmüller, Martin %E Benz, Dominik %E Hotho, Andreas %E Stumme, Gerd %T Conditional Random Fields For Local Adaptive Reference Extraction %U http://www.kde.cs.uni-kassel.de/conf/lwa10/papers/kdml21.pdf %X The accurate extraction of bibliographic information from scientific publications is an active field of research. Machine learning and sequence labeling approaches like Conditional Random Fields (CRF) are often applied for this reference extraction task, but still suffer from the ambiguity of reference notation. Reference sections apply a predefined style guide and contain only homogeneous references. Therefore, other references of the same paper or journal often provide evidence how the fields of a reference are correctly labeled. We propose a novel approach that exploits the similarities within a document. Our process model uses information of unlabeled documents directly during the extraction task in order to automatically adapt to the perceived style guide. This is implemented by changing the manifestation of the features for the applied CRF. The experimental results show considerable improvements compared to the common approach. We achieve an average F1 score of 96.7% and an instance accuracy of 85.4% on the test data set.