Natural Language Processing

In the field of Knowledge-Enriched NLP, we work on current topics of Natural Language Processing. Specifically, we are adapting and improving large language models (LLMs) such as BERT and its derivatives. Our particular focus lies in incorporating explicit knowledge, such as knowledge graphs.

Our application areas range from analyzing historical literature (where current language models struggle due to the length of the texts) to product reviews, and even to unconventional media forms for NLP, such as comments on http://twitch.tv. These media forms present their own challenges due to their unique language style. In addition to analyzing pure text, we also investigate the adaptability of NLP methods for processing mathematical equations.

In projects like Kallimachos or CLiGS we collaborate with literary scholars and work on literary and NLP research questions. In MOTIV, we work with psychologists to analyse the interaction between users and smart devices.

Detecting Scences in Fiction

Building machine learning based models that can segment literary texts into coherent parts.

Machine Learning and Knowledge Graphs

Leveraging Knowledge Graphs for NLP

Analysing Comments on Twitch.tv

Sentiment analysis of twitch comment streams.

Concluded Projects

Kallimachos - Building a complete text analysis pipeline, starting with OCR from paper and going up to high-level text mining.
CLiGS - CLiGS combines large text collections with innovative analysis methods and hermeneutic sensibility for context.

Publications

Zero-Shot Clickbait Spoiling by Rephrasing Titles as Questions Wangsadirdja, Dirk; Pfister, Jan; Kobs, Konstantin; Hotho, Andreas in Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023) (2023). 1090–1095.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
In this paper, we describe our approach to the clickbait spoiling task of SemEval 2023. The core idea behind our system is to leverage pre-trained models capable of Question Answering (QA) to extract the spoiler from article texts based on the clickbait title without any task-specific training. Since oftentimes, these titles are not phrased as questions, we automatically rephrase the clickbait titles as questions in order to better suit the pretraining task of the QA-capable models. Also, to fit as much relevant context into the model's limited input size as possible, we propose to reorder the sentences by their relevance using a semantic similarity model. Finally, we evaluate QA as well as text generation models (via prompting) to extract the spoiler from the text.Based on the validation data, our final model selects each of these components depending on the spoiler type and achieves satisfactory zero-shot results. The ideas described in this paper can easily be applied in fine-tuning settings.

@inproceedings{wangsadirdja-etal-2023-jack, abstract = {In this paper, we describe our approach to the clickbait spoiling task of SemEval 2023. The core idea behind our system is to leverage pre-trained models capable of Question Answering (QA) to extract the spoiler from article texts based on the clickbait title without any task-specific training. Since oftentimes, these titles are not phrased as questions, we automatically rephrase the clickbait titles as questions in order to better suit the pretraining task of the QA-capable models. Also, to fit as much relevant context into the model's limited input size as possible, we propose to reorder the sentences by their relevance using a semantic similarity model. Finally, we evaluate QA as well as text generation models (via prompting) to extract the spoiler from the text.Based on the validation data, our final model selects each of these components depending on the spoiler type and achieves satisfactory zero-shot results. The ideas described in this paper can easily be applied in fine-tuning settings.}, address = {Toronto, Canada}, author = {Wangsadirdja, Dirk and Pfister, Jan and Kobs, Konstantin and Hotho, Andreas}, booktitle = {Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023)}, keywords = {from:janpf}, month = {jul}, pages = {1090–1095}, publisher = {Association for Computational Linguistics}, title = {Zero-Shot Clickbait Spoiling by Rephrasing Titles as Questions}, year = 2023 }
Point me to your Opinion, {S}en{P}oi Pfister, Jan; Wankerl, Sebastian; Hotho, Andreas in Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022) (2022). 1313–1323.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
Structured Sentiment Analysis is the task of extracting sentiment tuples in a graph structure commonly from review texts. We adapt the Aspect-Based Sentiment Analysis pointer network BARTABSA to model this tuple extraction as a sequence prediction task and extend their output grammar to account for the increased complexity of Structured Sentiment Analysis. To predict structured sentiment tuples in languages other than English we swap BART for a multilingual mT5 and introduce a novel Output Length Regularization to mitigate overfitting to common target sequence lengths, thereby improving the performance of the model by up to 70{\%}. We evaluate our approach on seven datasets in five languages including a zero shot crosslingual setting.

@inproceedings{pfister-etal-2022-senpoi, abstract = {Structured Sentiment Analysis is the task of extracting sentiment tuples in a graph structure commonly from review texts. We adapt the Aspect-Based Sentiment Analysis pointer network BARTABSA to model this tuple extraction as a sequence prediction task and extend their output grammar to account for the increased complexity of Structured Sentiment Analysis. To predict structured sentiment tuples in languages other than English we swap BART for a multilingual mT5 and introduce a novel Output Length Regularization to mitigate overfitting to common target sequence lengths, thereby improving the performance of the model by up to 70{\%}. We evaluate our approach on seven datasets in five languages including a zero shot crosslingual setting.}, address = {Seattle, United States}, author = {Pfister, Jan and Wankerl, Sebastian and Hotho, Andreas}, booktitle = {Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)}, keywords = {from:janpf}, month = {jul}, pages = {1313–1323}, publisher = {Association for Computational Linguistics}, title = {Point me to your Opinion, {S}en{P}oi}, year = 2022 }
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 ]
- [ DOI ]
- [ Download ]
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{schmidt2021fairynet, 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 = {networks}, 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 }
Shared Task on Scene Segmentation @ KONVENS 2021 Zehe, Albin; Konle, Leonard; Guhr, Svenja; Dümpelmann, Lea; Gius, Evelyn; Hotho, Andreas; Jannidis, Fotis; Kaufmann, Lucas; Krug, Markus; Puppe, Frank; Reiter, Nils; Schreiber, Annekea in Shared Task on Scene Segmentation @ KONVENS 2021 (2021). 1–21.
- [ BibTeX ]
- [ URL ]
- [ Download ]
@inproceedings{zehe2021shared, author = {Zehe, Albin and Konle, Leonard and Guhr, Svenja 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}, booktitle = {Shared Task on Scene Segmentation @ KONVENS 2021}, keywords = {scenes}, pages = {1-21}, title = {Shared Task on Scene Segmentation @ KONVENS 2021}, 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 ]
- [ Download ]
@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 = {eacl}, publisher = {ACL}, title = {Detecting Scenes in Fiction: A new Segmentation Task}, year = 2021 }
LM4KG: Improving Common Sense Knowledge Graphs with Language Models Omeliyanenko, Janna; Zehe, Albin; Hettinger, Lena; Hotho, Andreas in International Semantic Web Conference (2020).
- [ BibTeX ]
- [ Download ]
@inproceedings{omeliyanenko2020reweight, author = {Omeliyanenko, Janna and Zehe, Albin and Hettinger, Lena and Hotho, Andreas}, booktitle = {International Semantic Web Conference}, keywords = {graph}, organization = {Springer}, title = {LM4KG: Improving Common Sense Knowledge Graphs with Language Models}, year = 2020 }
HarryMotions – Classifying Relationships in Harry Potter based on Emotion Analysis Zehe, Albin; Arns, Julia; Hettinger, Lena; Hotho, Andreas in 5th SwissText & 16th KONVENS Joint Conference (2020).
- [ BibTeX ]
- [ Download ]
@inproceedings{zehe2020harrymotions, author = {Zehe, Albin and Arns, Julia and Hettinger, Lena and Hotho, Andreas}, booktitle = {5th SwissText & 16th KONVENS Joint Conference}, keywords = {bert}, title = {HarryMotions – Classifying Relationships in Harry Potter based on Emotion Analysis}, year = 2020 }
Emote-Controlled: Obtaining Implicit Viewer Feedback through Emote based Sentiment Analysis on Comments of Popular Twitch.tv Channels Kobs, Konstantin; Zehe, Albin; Bernstetter, Armin; Chibane, Julian; Pfister, Jan; Tritscher, Julian; Hotho, Andreas in ACM Transactions on Social Computing (2020).
- [ BibTeX ]
- [ DOI ]
- [ Download ]
@article{kobs2020emotecontrolled, author = {Kobs, Konstantin and Zehe, Albin and Bernstetter, Armin and Chibane, Julian and Pfister, Jan and Tritscher, Julian and Hotho, Andreas}, journal = {ACM Transactions on Social Computing}, keywords = {sentiment-analysis}, title = {Emote-Controlled: Obtaining Implicit Viewer Feedback through Emote based Sentiment Analysis on Comments of Popular Twitch.tv Channels}, year = 2020 }
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 ]
- [ Download ]
@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 = {dh2019}, title = {Detection of Scenes in Fiction}, year = 2019 }
Analysing Direct Speech in German Novels Jannidis, Fotis; Konle, Leonard; Zehe, Albin; Hotho, Andreas; Krug, Markus in DHd 2018 (2018).
- [ BibTeX ]
- [ Download ]
@inproceedings{jannidis2018analysing, author = {Jannidis, Fotis and Konle, Leonard and Zehe, Albin and Hotho, Andreas and Krug, Markus}, booktitle = {DHd 2018}, keywords = {directspeech}, title = {Analysing Direct Speech in German Novels}, year = 2018 }
Burrows Zeta: Varianten und Evaluation Schöch, Christof; Calvo, José; Zehe, Albin; Hotho, Andreas in DHd 2018 (2018).
- [ BibTeX ]
- [ Download ]
@inproceedings{schoch2018burrows, author = {Schöch, Christof and Calvo, José and Zehe, Albin and Hotho, Andreas}, booktitle = {DHd 2018}, keywords = {zeta}, title = {Burrows Zeta: Varianten und Evaluation}, year = 2018 }
Burrows’ Zeta: Exploring and Evaluating Variants and Parameters Schöch, Christof; Schlör, Daniel; Zehe, Albin; Gebhard, Henning; Becker, Martin; Hotho, Andreas in DH (2018). 274–277.
- [ BibTeX ]
- [ URL ]
@inproceedings{schoech2018zeta, author = {Schöch, Christof and Schlör, Daniel and Zehe, Albin and Gebhard, Henning and Becker, Martin and Hotho, Andreas}, booktitle = {DH}, keywords = {zeta}, pages = {274-277}, title = {Burrows’ Zeta: Exploring and Evaluating Variants and Parameters}, year = 2018 }
A White-Box Model for Detecting Author Nationality by Linguistic Differences in Spanish Novels Zehe, Albin; Schlör, Daniel; Henny-Krahmer, Ulrike; Becker, Martin; Hotho, Andreas in DH (2018).
- [ BibTeX ]
- [ Download ]
@inproceedings{zehe2018whitebox, author = {Zehe, Albin and Schlör, Daniel and Henny-Krahmer, Ulrike and Becker, Martin and Hotho, Andreas}, booktitle = {DH}, keywords = {classification}, organization = {ADHO}, title = {A White-Box Model for Detecting Author Nationality by Linguistic Differences in Spanish Novels}, year = 2018 }
Towards Sentiment Analysis on German Literature Zehe, Albin; Becker, Martin; Jannidis, Fotis; Hotho, Andreas (2017).
- [ BibTeX ]
- [ Download ]
@inproceedings{zehe2017sentiment, author = {Zehe, Albin and Becker, Martin and Jannidis, Fotis and Hotho, Andreas}, keywords = {from:albinzehe}, title = {Towards Sentiment Analysis on German Literature}, year = 2017 }
Straight Talk! Automatic Recognition of Direct Speech in Nineteenth-Century French Novels. Sch{\"o}ch, Christof; Schl{\"o}r, Daniel; Popp, Stefanie; Brunner, Annelen; Henny, Ulrike; Tello, Jos{\’e} Calvo in DH (2016). 346–353.
- [ BibTeX ]
- [ Download ]
@inproceedings{schoch2016straight, author = {Sch{\"o}ch, Christof and Schl{\"o}r, Daniel and Popp, Stefanie and Brunner, Annelen and Henny, Ulrike and Tello, Jos{\'e} Calvo}, booktitle = {DH}, keywords = {directspeech}, pages = {346–353}, title = {Straight Talk! Automatic Recognition of Direct Speech in Nineteenth-Century French Novels.}, year = 2016 }
Analyzing Features for the Detection of Happy Endings in German Novels Jannidis, Fotis; Reger, Isabella; Zehe, Albin; Becker, Martin; Hettinger, Lena; Hotho, Andreas (2016).
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
With regard to a computational representation of literary plot, this paper looks at the use of sentiment analysis for happy ending detection in German novels. Its focus lies on the investigation of previously proposed sentiment features in order to gain insight about the relevance of specific features on the one hand and the implications of their performance on the other hand. Therefore, we study various partitionings of novels, considering the highly variable concept of "ending". We also show that our approach, even though still rather simple, can potentially lead to substantial findings relevant to literary studies.

@misc{jannidis2016analyzing, abstract = {With regard to a computational representation of literary plot, this paper looks at the use of sentiment analysis for happy ending detection in German novels. Its focus lies on the investigation of previously proposed sentiment features in order to gain insight about the relevance of specific features on the one hand and the implications of their performance on the other hand. Therefore, we study various partitionings of novels, considering the highly variable concept of "ending". We also show that our approach, even though still rather simple, can potentially lead to substantial findings relevant to literary studies.}, author = {Jannidis, Fotis and Reger, Isabella and Zehe, Albin and Becker, Martin and Hettinger, Lena and Hotho, Andreas}, keywords = {from:albinzehe}, note = {cite arxiv:1611.09028}, title = {Analyzing Features for the Detection of Happy Endings in German Novels}, year = 2016 }
Prediction of Happy Endings in German Novels Zehe, Albin; Becker, Martin; Hettinger, Lena; Hotho, Andreas; Reger, Isabella; Jannidis, Fotis in Proceedings of the Workshop on Interactions between Data Mining and Natural Language Processing 2016, P. Cellier, T. Charnois, A. Hotho, S. Matwin, M.-F. Moens, Y. Toussaint (eds.) (2016). 9–16.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
Identifying plot structure in novels is a valuable step towards automatic processing of literary corpora. We present an approach to classify novels as either having a happy ending or not. To achieve this, we use features based on different sentiment lexica as input for an SVM- classifier, which yields an average F1-score of about 73%.

@inproceedings{zehe2016prediction, abstract = {Identifying plot structure in novels is a valuable step towards automatic processing of literary corpora. We present an approach to classify novels as either having a happy ending or not. To achieve this, we use features based on different sentiment lexica as input for an SVM- classifier, which yields an average F1-score of about 73%.}, author = {Zehe, Albin and Becker, Martin and Hettinger, Lena and Hotho, Andreas and Reger, Isabella and Jannidis, Fotis}, booktitle = {Proceedings of the Workshop on Interactions between Data Mining and Natural Language Processing 2016}, editor = {Cellier, Peggy and Charnois, Thierry and Hotho, Andreas and Matwin, Stan and Moens, Marie-Francine and Toussaint, Yannick}, keywords = {novels}, month = {jul}, pages = {9-16}, title = {Prediction of Happy Endings in German Novels}, year = 2016 }
Significance Testing for the Classification of Literary Subgenres Hettinger, Lena; Jannidis, Fotis; Reger, Isabella; Hotho, Andreas in DH 2016 (2016).
- [ BibTeX ]
- [ Download ]
@inproceedings{hettinger2016significance, author = {Hettinger, Lena and Jannidis, Fotis and Reger, Isabella and Hotho, Andreas}, booktitle = {DH 2016}, keywords = {classification}, title = {Significance Testing for the Classification of Literary Subgenres}, year = 2016 }
Classification of Literary Subgenres Hettinger, Lena; Jannidis, Fotis; Reger, Isabella; Hotho, Andreas in DHd 2016 (2016).
- [ BibTeX ]
- [ Download ]
@inproceedings{hettinger2016classification, author = {Hettinger, Lena and Jannidis, Fotis and Reger, Isabella and Hotho, Andreas}, booktitle = {DHd 2016}, keywords = {classification}, title = {Classification of Literary Subgenres}, year = 2016 }
Genre classification on German novels Hettinger, Lena; Becker, Martin; Reger, Isabella; Jannidis, Fotis; Hotho, Andreas in Proceedings of the 12th International Workshop on Text-based Information Retrieval (2015).
- [ BibTeX ]
- [ URL ]
- [ Download ]
@inproceedings{schwemmlein2015genre, author = {Hettinger, Lena and Becker, Martin and Reger, Isabella and Jannidis, Fotis and Hotho, Andreas}, booktitle = {Proceedings of the 12th International Workshop on Text-based Information Retrieval}, keywords = {classification}, title = {Genre classification on German novels}, year = 2015 }

Natural Language Processing

Projects

LitBERT

KILiMod

MOTIV