Jan Pfister, M.Sc.

Chair of Data Science (Informatik X)
University of Würzburg
Campus Hubland Nord
Emil-Fischer-Straße 50
97074 Würzburg
Germany

Email: pfister[at]informatik.uni-wuerzburg.de

Phone: (+49 931) 31 - 81934

Office: Room 50.03.020 (Institutsgebäude Künstliche Intelligenz)

PGP Fingerprint: 9131 6BAF 85DE CFB3 AF89 86C9 568C 615A F18B C9C0

Research Interests & Projects

I work in the field of Natural Language Processing (NLP) and in particular, I am interested in developing novel methods for understanding and extracting meaning from text. My work focuses on using large language models also in combination with pointer networks to capture the complexities of human language. I am currently working on applying these techniques to the task of aspect-based sentiment analysis, in order to extract fine-grained sentiment information from text. Also I'm working on advancing the German NLP landscape with artifacts like the first comprehensive benchmark or German pretrained models from scratch (like LLäMmlein, or ModernGBERT).

I joined the DMIR group for my PhD studies after receiving my master's degree in Computer Science at the University of Würzburg in 2021 and currently I'm responsible for BibSonomy.

Awards & Stuff

First Place at SemEval 24 Shared Task 4, and Best Paper Honorable Mention Award over all tasks
First Place at SemEval 25 Shared Task 2, and Best Paper Award Task 2

Teaching

Seminar: Ausgewählte Themen des Machine Learning (SS'21 + WS '21 + WS'24)
Lecture: Information Retrieval (SS '22)
Project: Machine Learning in Natural Language Processing (since '22)
Lecture: Text Mining (WS '23)

Publications

2025[ to top ]

BARTABSA++: Revisiting BARTABSA with Decoder LLMs. Pfister, Jan; Völker, Tom; Vlasjuk, Anton; Hotho, Andreas. In Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025), H. Fei, K. Tu, Y. Zhang, X. Hu, W. Han, Z. Jia, Z. Zheng, Y. Cao, M. Zhang, W. Lu, N. Siddharth, L. Ovrelid, N. Xue, Y. Zhang (eds.), pp. 115–128. Association for Computational Linguistics, Vienna, Austria, 2025.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
- [ BibSonomy-Post ]
We revisit the BARTABSA framework for aspect-based sentiment analysis with modern decoder LLMs to assess the importance of explicit structure modeling today. Our updated implementation - BARTABSA++ - features architectural enhancements that boost performance and training stability.Systematic testing with various encoder-decoder architectures shows that BARTABSA++ with BART-Large achieves state-of-the-art results, even surpassing a finetuned GPT-4o model.Our analysis indicates the encoder's representational quality is vital, while the decoder's role is minimal, explaining the limited benefits of scaling decoder-only LLMs for this task. These findings underscore the complementary roles of explicit structured modeling and large language models, indicating structured approaches remain competitive for tasks requiring precise relational information extraction.

@inproceedings{pfister-etal-2025-bartabsa, abstract = {We revisit the BARTABSA framework for aspect-based sentiment analysis with modern decoder LLMs to assess the importance of explicit structure modeling today. Our updated implementation - BARTABSA++ - features architectural enhancements that boost performance and training stability.Systematic testing with various encoder-decoder architectures shows that BARTABSA++ with BART-Large achieves state-of-the-art results, even surpassing a finetuned GPT-4o model.Our analysis indicates the encoder{'}s representational quality is vital, while the decoder{'}s role is minimal, explaining the limited benefits of scaling decoder-only LLMs for this task. These findings underscore the complementary roles of explicit structured modeling and large language models, indicating structured approaches remain competitive for tasks requiring precise relational information extraction.}, address = {Vienna, Austria}, author = {Pfister, Jan and V{\"o}lker, Tom and Vlasjuk, Anton and Hotho, Andreas}, booktitle = {Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025)}, editor = {Fei, Hao and Tu, Kewei and Zhang, Yuhui and Hu, Xiang and Han, Wenjuan and Jia, Zixia and Zheng, Zilong and Cao, Yixin and Zhang, Meishan and Lu, Wei and Siddharth, N. and {\O}vrelid, Lilja and Xue, Nianwen and Zhang, Yue}, keywords = {author:pfister}, month = {08}, pages = {115–128}, publisher = {Association for Computational Linguistics}, title = {{BARTABSA}++: Revisiting {BARTABSA} with Decoder {LLM}s}, year = 2025 }
SALT at SemEval-2025 Task 2: A SQL-based Approach for LLM-Free Entity-Aware-Translation. Völker, Tom; Pfister, Jan; Hotho, Andreas. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), S. Rosenthal, A. Rosá, D. Ghosh, M. Zampieri (eds.), pp. 852–864. Association for Computational Linguistics, Vienna, Austria, 2025.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
- [ BibSonomy-Post ]
Entity-aware machine translation faces significant challenges when translating culturally-adapted named entities that require knowledge beyond the source text.We present SALT (SQL-based Approach for LLM-Free Entity-Aware-Translation), a parameter-efficient system for the SemEval-2025 Task 2.Our approach combines SQL-based entity retrieval with constrained neural translation via logit biasing and explicit entity annotations.Despite its simplicity, it achieves state-of-the-art performance (First Place) among approaches not using gold-standard data, while requiring far less computation than LLM-based methods.Our ablation studies show simple SQL-based retrieval rivals complex neural models, and strategic model refinement outperforms increased model complexity.SALT offers an alternative to resource-intensive LLM-based approaches, achieving comparable results with only a fraction of the parameters.

@inproceedings{volker-etal-2025-salt, abstract = {Entity-aware machine translation faces significant challenges when translating culturally-adapted named entities that require knowledge beyond the source text.We present SALT (SQL-based Approach for LLM-Free Entity-Aware-Translation), a parameter-efficient system for the SemEval-2025 Task 2.Our approach combines SQL-based entity retrieval with constrained neural translation via logit biasing and explicit entity annotations.Despite its simplicity, it achieves state-of-the-art performance (First Place) among approaches not using gold-standard data, while requiring far less computation than LLM-based methods.Our ablation studies show simple SQL-based retrieval rivals complex neural models, and strategic model refinement outperforms increased model complexity.SALT offers an alternative to resource-intensive LLM-based approaches, achieving comparable results with only a fraction of the parameters.}, address = {Vienna, Austria}, author = {Völker, Tom and Pfister, Jan and Hotho, Andreas}, booktitle = {Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)}, editor = {Rosenthal, Sara and Ros{\'a}, Aiala and Ghosh, Debanjan and Zampieri, Marcos}, keywords = {author:pfister}, month = {07}, pages = {852–864}, publisher = {Association for Computational Linguistics}, title = {{SALT} at {S}em{E}val-2025 Task 2: A {SQL}-based Approach for {LLM}-Free Entity-Aware-Translation}, year = 2025 }
CAIDAS at SemEval-2025 Task 7: Enriching Sparse Datasets with LLM-Generated Content for Improved Information Retrieval. Benchert, Dominik; Meßlinger, Severin; Goller, Sven; Kaiser, Jonas; Pfister, Jan; Hotho, Andreas. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), S. Rosenthal, A. Rosá, D. Ghosh, M. Zampieri (eds.), pp. 1623–1638. Association for Computational Linguistics, Vienna, Austria, 2025.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
- [ BibSonomy-Post ]
The focus of SemEval-2024 Task 7 is the retrieval of relevant fact-checks for social media posts across multiple languages. We approach this task with an enhanced bi-encoder retrieval setup, which is designed to match social media posts with relevant fact-checks using synthetic data from LLMs. We explored and analyzed two main approaches for generating synthetic posts. Either based on existing fact-checks or on existing posts. Our approach achieved an S@10 score of 89.53% for the monolingual task and 74.48% for the crosslingual task, ranking 16th out of 28 and 13th out of 29, respectively. Without data augmentation, scores would have been 88.69 (17th) and 72.93 (15th).

@inproceedings{benchert-etal-2025-caidas, abstract = {The focus of SemEval-2024 Task 7 is the retrieval of relevant fact-checks for social media posts across multiple languages. We approach this task with an enhanced bi-encoder retrieval setup, which is designed to match social media posts with relevant fact-checks using synthetic data from LLMs. We explored and analyzed two main approaches for generating synthetic posts. Either based on existing fact-checks or on existing posts. Our approach achieved an S@10 score of 89.53{\%} for the monolingual task and 74.48{\%} for the crosslingual task, ranking 16th out of 28 and 13th out of 29, respectively. Without data augmentation, scores would have been 88.69 (17th) and 72.93 (15th).}, address = {Vienna, Austria}, author = {Benchert, Dominik and Me{\ss}linger, Severin and Goller, Sven and Kaiser, Jonas and Pfister, Jan and Hotho, Andreas}, booktitle = {Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)}, editor = {Rosenthal, Sara and Ros{\'a}, Aiala and Ghosh, Debanjan and Zampieri, Marcos}, keywords = {author:pfister}, month = {07}, pages = {1623–1638}, publisher = {Association for Computational Linguistics}, title = {{CAIDAS} at {S}em{E}val-2025 Task 7: Enriching Sparse Datasets with {LLM}-Generated Content for Improved Information Retrieval}, year = 2025 }
Identifying Axiomatic Mathematical Transformation Steps using Tree-Structured Pointer Networks. Wankerl, Sebastian; Pfister, Jan; Dulny, Andrzej; Götz, Gerhard; Hotho, Andreas. In Transactions on Machine Learning Research. 2025.
- [ BibTeX ]
- [ URL ]
- [ Download ]
- [ BibSonomy-Post ]
@article{wankerl2025identifying, author = {Wankerl, Sebastian and Pfister, Jan and Dulny, Andrzej and G{\"o}tz, Gerhard and Hotho, Andreas}, journal = {Transactions on Machine Learning Research}, keywords = {author:pfister}, title = {Identifying Axiomatic Mathematical Transformation Steps using Tree-Structured Pointer Networks}, year = 2025 }
ModernGBERT: German-only 1B Encoder Model Trained from Scratch. Ehrmanntraut, Anton; Wunderle, Julia; Pfister, Jan; Jannidis, Fotis; Hotho, Andreas. 2025.
- [ BibTeX ]
- [ URL ]
- [ Download ]
- [ BibSonomy-Post ]
@misc{ehrmanntraut2025moderngbertgermanonly1bencoder, author = {Ehrmanntraut, Anton and Wunderle, Julia and Pfister, Jan and Jannidis, Fotis and Hotho, Andreas}, keywords = {author:pfister}, title = {ModernGBERT: German-only 1B Encoder Model Trained from Scratch}, year = 2025 }
LLäMmlein: Transparent, Compact and Competitive German-Only Language Models from Scratch. Pfister, Jan; Wunderle, Julia; Hotho, Andreas. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), W. Che, J. Nabende, E. Shutova, M. T. Pilehvar (eds.), pp. 2227–2246. Association for Computational Linguistics, Vienna, Austria, 2025.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
- [ BibSonomy-Post ]
We transparently create two German-only decoder models, LLäMmlein 120M and 1B, from scratch and publish them, along with the training data, for the (German) NLP research community to use. The model training involved several key steps, including data preprocessing/filtering, the creation of a German tokenizer, the training itself, as well as the evaluation of the final models on various benchmarks, also against existing models. Throughout the training process, multiple checkpoints were saved in equal intervals and analyzed using the German SuperGLEBer benchmark to gain insights into the models' learning process.Compared to state-of-the-art models on the SuperGLEBer benchmark, both LLäMmlein models performed competitively, consistently matching or surpassing models with similar parameter sizes. The results show that the models' quality scales with size as expected, but performance improvements on some tasks plateaued early during training, offering valuable insights into resource allocation for future models.

@inproceedings{pfister-etal-2025-llammlein, abstract = {We transparently create two German-only decoder models, LL{\"a}Mmlein 120M and 1B, from scratch and publish them, along with the training data, for the (German) NLP research community to use. The model training involved several key steps, including data preprocessing/filtering, the creation of a German tokenizer, the training itself, as well as the evaluation of the final models on various benchmarks, also against existing models. Throughout the training process, multiple checkpoints were saved in equal intervals and analyzed using the German SuperGLEBer benchmark to gain insights into the models' learning process.Compared to state-of-the-art models on the SuperGLEBer benchmark, both LL{\"a}Mmlein models performed competitively, consistently matching or surpassing models with similar parameter sizes. The results show that the models' quality scales with size as expected, but performance improvements on some tasks plateaued early during training, offering valuable insights into resource allocation for future models.}, address = {Vienna, Austria}, author = {Pfister, Jan and Wunderle, Julia and Hotho, Andreas}, booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher}, keywords = {author:pfister}, month = {07}, pages = {2227–2246}, publisher = {Association for Computational Linguistics}, title = {LLäMmlein: Transparent, Compact and Competitive {G}erman-Only Language Models from Scratch}, year = 2025 }

2024[ to top ]

Pollice Verso at SemEval-2024 Task 6: The Roman Empire Strikes Back. Kobs, Konstantin; Pfister, Jan; Hotho, Andreas. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), A. K. Ojha, A. S. Dougruöz, H. Tayyar Madabushi, G. Da San Martino, S. Rosenthal, A. Rosá (eds.), pp. 1529–1536. Association for Computational Linguistics, Mexico City, Mexico, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
- [ BibSonomy-Post ]
We present an intuitive approach for hallucination detection in LLM outputs that is modeled after how humans would go about this task. We engage several LLM ``experts'' to independently assess whether a response is hallucinated. For this we select recent and popular LLMs smaller than 7B parameters. By analyzing the log probabilities for tokens that signal a positive or negative judgment, we can determine the likelihood of hallucination. Additionally, we enhance the performance of our ``experts'' by automatically refining their prompts using the recently introduced OPRO framework. Furthermore, we ensemble the replies of the different experts in a uniform or weighted manner, which builds a quorum from the expert replies. Overall this leads to accuracy improvements of up to 10.6 p.p. compared to the challenge baseline. We show that a Zephyr 3B model is well suited for the task. Our approach can be applied in the model-agnostic and model-aware subtasks without modification and is flexible and easily extendable to related tasks.

@inproceedings{kobs-etal-2024-pollice, abstract = {We present an intuitive approach for hallucination detection in LLM outputs that is modeled after how humans would go about this task. We engage several LLM {``}experts{''} to independently assess whether a response is hallucinated. For this we select recent and popular LLMs smaller than 7B parameters. By analyzing the log probabilities for tokens that signal a positive or negative judgment, we can determine the likelihood of hallucination. Additionally, we enhance the performance of our {``}experts{''} by automatically refining their prompts using the recently introduced OPRO framework. Furthermore, we ensemble the replies of the different experts in a uniform or weighted manner, which builds a quorum from the expert replies. Overall this leads to accuracy improvements of up to 10.6 p.p. compared to the challenge baseline. We show that a Zephyr 3B model is well suited for the task. Our approach can be applied in the model-agnostic and model-aware subtasks without modification and is flexible and easily extendable to related tasks.}, address = {Mexico City, Mexico}, author = {Kobs, Konstantin and Pfister, Jan and Hotho, Andreas}, booktitle = {Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)}, editor = {Ojha, Atul Kr. and Do{\u{g}}ru\"oz, A. Seza and Tayyar Madabushi, Harish and Da San Martino, Giovanni and Rosenthal, Sara and Ros\'a, Aiala}, keywords = {author:pfister}, month = {06}, pages = {1529–1536}, publisher = {Association for Computational Linguistics}, title = {Pollice Verso at SemEval-2024 Task 6: The Roman Empire Strikes Back}, year = 2024 }
From Chat to Publication Management: Organizing your related work using BibSonomy & LLMs. Völker, Tom; Pfister, Jan; Koopmann, Tobias; Hotho, Andreas. In Proceedings of the 2024 Conference on Human Information Interaction and Retrieval, of CHIIR ’24, pp. 386–390. Association for Computing Machinery, <conf-loc>, <city>Sheffield</city>, <country>United Kingdom</country>, </conf-loc>, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
- [ BibSonomy-Post ]
The ever-growing corpus of scientific literature presents significant challenges for researchers with respect to discovery, management, and annotation of relevant publications. Traditional platforms like Semantic Scholar, BibSonomy, and Zotero offer tools for literature management, but largely require manual laborious and error-prone input of tags and metadata. Here, we introduce a novel retrieval augmented generation system that leverages chat-based large language models (LLMs) to streamline and enhance the process of publication management. It provides a unified chat-based interface, enabling intuitive interactions with various backends, including Semantic Scholar, BibSonomy, and the Zotero Webscraper. It supports two main use-cases: (1) Explorative Search & Retrieval - leveraging LLMs to search for and retrieve both specific and general scientific publications, while addressing the challenges of content hallucination and data obsolescence; and (2) Cataloguing & Management - aiding in the organization of personal publication libraries, in this case BibSonomy, by automating the addition of metadata and tags, while facilitating manual edits and updates. We compare our system to different LLM models in three different settings, including a user study, and we can show its advantages in different metrics.

@inproceedings{10.1145/3627508.3638298, abstract = {The ever-growing corpus of scientific literature presents significant challenges for researchers with respect to discovery, management, and annotation of relevant publications. Traditional platforms like Semantic Scholar, BibSonomy, and Zotero offer tools for literature management, but largely require manual laborious and error-prone input of tags and metadata. Here, we introduce a novel retrieval augmented generation system that leverages chat-based large language models (LLMs) to streamline and enhance the process of publication management. It provides a unified chat-based interface, enabling intuitive interactions with various backends, including Semantic Scholar, BibSonomy, and the Zotero Webscraper. It supports two main use-cases: (1) Explorative Search \& Retrieval - leveraging LLMs to search for and retrieve both specific and general scientific publications, while addressing the challenges of content hallucination and data obsolescence; and (2) Cataloguing \& Management - aiding in the organization of personal publication libraries, in this case BibSonomy, by automating the addition of metadata and tags, while facilitating manual edits and updates. We compare our system to different LLM models in three different settings, including a user study, and we can show its advantages in different metrics.}, address = {New York, NY, USA}, author = {Völker, Tom and Pfister, Jan and Koopmann, Tobias and Hotho, Andreas}, booktitle = {Proceedings of the 2024 Conference on Human Information Interaction and Retrieval}, keywords = {author:pfister}, month = {05}, pages = {386–390}, publisher = {Association for Computing Machinery}, series = {CHIIR '24}, title = {From Chat to Publication Management: Organizing your related work using BibSonomy & LLMs}, year = 2024 }
SuperGLEBer: German Language Understanding Evaluation Benchmark. Pfister, Jan; Hotho, Andreas. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), K. Duh, H. Gomez, S. Bethard (eds.), pp. 7904–7923. Association for Computational Linguistics, Mexico City, Mexico, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
- [ BibSonomy-Post ]
We assemble a broad Natural Language Understanding benchmark suite for the German language and consequently evaluate a wide array of existing German-capable models in order to create a better understanding of the current state of German LLMs. Our benchmark consists of 29 different tasks ranging over different types such as document classification, sequence tagging, sentence similarity, and question answering, on which we evaluate 10 different German-pretrained models, thereby charting the landscape of German LLMs. In our comprehensive evaluation we find that encoder models are a good choice for most tasks, but also that the largest encoder model does not necessarily perform best for all tasks. We make our benchmark suite and a leaderboard publically available at https://supergleber.professor-x.de and encourage the community to contribute new tasks and evaluate more models on it (https://github.com/LSX-UniWue/SuperGLEBer).

@inproceedings{pfister-hotho-2024-supergleber, abstract = {We assemble a broad Natural Language Understanding benchmark suite for the German language and consequently evaluate a wide array of existing German-capable models in order to create a better understanding of the current state of German LLMs. Our benchmark consists of 29 different tasks ranging over different types such as document classification, sequence tagging, sentence similarity, and question answering, on which we evaluate 10 different German-pretrained models, thereby charting the landscape of German LLMs. In our comprehensive evaluation we find that encoder models are a good choice for most tasks, but also that the largest encoder model does not necessarily perform best for all tasks. We make our benchmark suite and a leaderboard publically available at https://supergleber.professor-x.de and encourage the community to contribute new tasks and evaluate more models on it (https://github.com/LSX-UniWue/SuperGLEBer).}, address = {Mexico City, Mexico}, author = {Pfister, Jan and Hotho, Andreas}, booktitle = {Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)}, editor = {Duh, Kevin and Gomez, Helena and Bethard, Steven}, keywords = {author:pfister}, month = {06}, pages = {7904–7923}, publisher = {Association for Computational Linguistics}, title = {{S}uper{GLEB}er: {G}erman Language Understanding Evaluation Benchmark}, year = 2024 }
OtterlyObsessedWithSemantics at SemEval-2024 Task 4: Developing a Hierarchical Multi-Label Classification Head for Large Language Models. Wunderle, Julia; Schubert, Julian; Cacciatore, Antonella; Zehe, Albin; Pfister, Jan; Hotho, Andreas. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), A. K. Ojha, A. S. Dougruöz, H. Tayyar Madabushi, G. Da San Martino, S. Rosenthal, A. Rosá (eds.), pp. 602–612. Association for Computational Linguistics, Mexico City, Mexico, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
- [ BibSonomy-Post ]
For our submission for Subtask 1, we developed a custom classification head that is designed to be applied atop of a Large Language Model. We reconstructed the hierarchy across multiple fully connected layers, allowing us to incorporate previous foundational decisions in subsequent, more fine-grained layers. To find the best hyperparameters, we conducted a grid-search and to compete in the multilingual setting, we translated all documents to English.

@inproceedings{wunderle-etal-2024-otterlyobsessedwithsemantics, abstract = {For our submission for Subtask 1, we developed a custom classification head that is designed to be applied atop of a Large Language Model. We reconstructed the hierarchy across multiple fully connected layers, allowing us to incorporate previous foundational decisions in subsequent, more fine-grained layers. To find the best hyperparameters, we conducted a grid-search and to compete in the multilingual setting, we translated all documents to English.}, address = {Mexico City, Mexico}, author = {Wunderle, Julia and Schubert, Julian and Cacciatore, Antonella and Zehe, Albin and Pfister, Jan and Hotho, Andreas}, booktitle = {Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)}, editor = {Ojha, Atul Kr. and Do{\u{g}}ru{\"o}z, A. Seza and Tayyar Madabushi, Harish and Da San Martino, Giovanni and Rosenthal, Sara and Ros{\'a}, Aiala}, keywords = {author:pfister}, month = {06}, pages = {602–612}, publisher = {Association for Computational Linguistics}, title = {{O}tterly{O}bsessed{W}ith{S}emantics at {S}em{E}val-2024 Task 4: Developing a Hierarchical Multi-Label Classification Head for Large Language Models}, year = 2024 }

2023[ to top ]

Pointer Networks: A Unified Approach to Extracting German Opinions. Wunderle, Julia; Pfister, Jan; Hotho, Andreas. In Proceedings of the 19th Conference on Natural Language Processing (KONVENS 2023), M. Georges, A. Herygers, A. Friedrich, B. Roth (eds.), pp. 127–138. Association for Computational Lingustics, Ingolstadt, Germany, 2023.
- [ BibTeX ]
- [ URL ]
- [ Download ]
- [ BibSonomy-Post ]
@inproceedings{wunderle-etal-2023-pointer, address = {Ingolstadt, Germany}, author = {Wunderle, Julia and Pfister, Jan and Hotho, Andreas}, booktitle = {Proceedings of the 19th Conference on Natural Language Processing (KONVENS 2023)}, editor = {Georges, Munir and Herygers, Aaricia and Friedrich, Annemarie and Roth, Benjamin}, keywords = {from:janpf}, month = {09}, pages = {127–138}, publisher = {Association for Computational Lingustics}, title = {Pointer Networks: A Unified Approach to Extracting {G}erman Opinions}, year = 2023 }
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), pp. 1090–1095. Association for Computational Linguistics, Toronto, Canada, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
- [ BibSonomy-Post ]
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 = {07}, pages = {1090–1095}, publisher = {Association for Computational Linguistics}, title = {Zero-Shot Clickbait Spoiling by Rephrasing Titles as Questions}, year = 2023 }
Optimizing Medical Service Request Processes through Language Modeling and Semantic Search. Schlör, Daniel; Pfister, Jan; Hotho, Andreas. In 2023 the 7th International Conference on Medical and Health Informatics (ICMHI), of ICMHI 2023, pp. 136–141. Association for Computing Machinery, Kyoto, Japan, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
- [ BibSonomy-Post ]
Medical service requests are a crucial part of the workflow in hospitals and healthcare organizations. However, the process of requesting medical services can be time consuming and can require physicians and medical personnel to navigate complex interfaces and enter detailed information about the requested service. In this paper, we propose a system that uses machine learning techniques such as large language models and semantic search to optimize the process of requesting medical services. Our approach enables physicians to request medical services using natural language rather than navigating complex interfaces, allowing for more efficient and flexible interactions with hospital information systems. We evaluate our approach on real-world data and discuss the implications of our work for the future of digital health care. Our results suggest that our approach has the potential to streamline the process of requesting medical services and reduce the time and manual effort required in the daily hospital routine.

@inproceedings{10.1145/3608298.3608324, abstract = {Medical service requests are a crucial part of the workflow in hospitals and healthcare organizations. However, the process of requesting medical services can be time consuming and can require physicians and medical personnel to navigate complex interfaces and enter detailed information about the requested service. In this paper, we propose a system that uses machine learning techniques such as large language models and semantic search to optimize the process of requesting medical services. Our approach enables physicians to request medical services using natural language rather than navigating complex interfaces, allowing for more efficient and flexible interactions with hospital information systems. We evaluate our approach on real-world data and discuss the implications of our work for the future of digital health care. Our results suggest that our approach has the potential to streamline the process of requesting medical services and reduce the time and manual effort required in the daily hospital routine.}, address = {New York, NY, USA}, author = {Schl\"{o}r, Daniel and Pfister, Jan and Hotho, Andreas}, booktitle = {2023 the 7th International Conference on Medical and Health Informatics (ICMHI)}, keywords = {author:pfister}, pages = {136–141}, publisher = {Association for Computing Machinery}, series = {ICMHI 2023}, title = {Optimizing Medical Service Request Processes through Language Modeling and Semantic Search}, year = 2023 }
Long-Term Effects of Perceived Friendship with Intelligent Voice Assistants on Usage Behavior, User Experience, and Social Perceptions. Wienrich, Carolin; Carolus, Astrid; Markus, André; Augustin, Yannik; Pfister, Jan; Hotho, Andreas. In Computers, 12(4). 2023.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
- [ BibSonomy-Post ]
Social patterns and roles can develop when users talk to intelligent voice assistants (IVAs) daily. The current study investigates whether users assign different roles to devices and how this affects their usage behavior, user experience, and social perceptions. Since social roles take time to establish, we equipped 106 participants with Alexa or Google assistants and some smart home devices and observed their interactions for nine months. We analyzed diverse subjective (questionnaire) and objective data (interaction data). By combining social science and data science analyses, we identified two distinct clusters—users who assigned a friendship role to IVAs over time and users who did not. Interestingly, these clusters exhibited significant differences in their usage behavior, user experience, and social perceptions of the devices. For example, participants who assigned a role to IVAs attributed more friendship to them used them more frequently, reported more enjoyment during interactions, and perceived more empathy for IVAs. In addition, these users had distinct personal requirements, for example, they reported more loneliness. This study provides valuable insights into the role-specific effects and consequences of voice assistants. Recent developments in conversational language models such as ChatGPT suggest that the findings of this study could make an important contribution to the design of dialogic human–AI interactions.

@article{wienrich2023longterm, abstract = {Social patterns and roles can develop when users talk to intelligent voice assistants (IVAs) daily. The current study investigates whether users assign different roles to devices and how this affects their usage behavior, user experience, and social perceptions. Since social roles take time to establish, we equipped 106 participants with Alexa or Google assistants and some smart home devices and observed their interactions for nine months. We analyzed diverse subjective (questionnaire) and objective data (interaction data). By combining social science and data science analyses, we identified two distinct clusters—users who assigned a friendship role to IVAs over time and users who did not. Interestingly, these clusters exhibited significant differences in their usage behavior, user experience, and social perceptions of the devices. For example, participants who assigned a role to IVAs attributed more friendship to them used them more frequently, reported more enjoyment during interactions, and perceived more empathy for IVAs. In addition, these users had distinct personal requirements, for example, they reported more loneliness. This study provides valuable insights into the role-specific effects and consequences of voice assistants. Recent developments in conversational language models such as ChatGPT suggest that the findings of this study could make an important contribution to the design of dialogic human–AI interactions.}, author = {Wienrich, Carolin and Carolus, Astrid and Markus, André and Augustin, Yannik and Pfister, Jan and Hotho, Andreas}, journal = {Computers}, keywords = {from:janpf}, number = 4, title = {Long-Term Effects of Perceived Friendship with Intelligent Voice Assistants on Usage Behavior, User Experience, and Social Perceptions}, volume = 12, year = 2023 }
Higher-Order DeepTrails: Unified Approach to *Trails. Koopmann, Tobias; Pfister, Jan; Markus, André; Carolus, Astrid; Wienrich, Carolin; Hotho, Andreas. In Lernen, Wissen, Daten, Analysen (LWDA) Conference Proceedings, Marburg, Germany, October 9-11, 2023, Vol. 3630 of CEUR Workshop Proceedings, M. Leyer, J. Wichmann (eds.), pp. 372–386. CEUR-WS.org, 2023.
- [ BibTeX ]
- [ URL ]
- [ Download ]
- [ BibSonomy-Post ]
@inproceedings{DBLP:conf/lwa/Koopmann23, author = {Koopmann, Tobias and Pfister, Jan and Markus, André and Carolus, Astrid and Wienrich, Carolin and Hotho, Andreas}, booktitle = {Lernen, Wissen, Daten, Analysen {(LWDA)} Conference Proceedings, Marburg, Germany, October 9-11, 2023}, editor = {Leyer, Michael and Wichmann, Johannes}, keywords = {author:pfister}, pages = {372–386}, publisher = {CEUR-WS.org}, series = {{CEUR} Workshop Proceedings}, title = {Higher-Order DeepTrails: Unified Approach to *Trails}, volume = 3630, year = 2023 }

2022[ to top ]

Point me to your Opinion, SenPoi. Pfister, Jan; Wankerl, Sebastian; Hotho, Andreas. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pp. 1313–1323. Association for Computational Linguistics, Seattle, United States, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
- [ BibSonomy-Post ]
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 = {07}, pages = {1313–1323}, publisher = {Association for Computational Linguistics}, title = {Point me to your Opinion, {S}en{P}oi}, year = 2022 }

2021[ to top ]

Self-Supervised Multi-Task Pretraining Improves Image Aesthetic Assessment. Pfister, Jan; Kobs, Konstantin; Hotho, Andreas. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 816–825. 2021.
- [ BibTeX ]
- [ Download ]
- [ BibSonomy-Post ]
@inproceedings{Pfister_2021_CVPR, author = {Pfister, Jan and Kobs, Konstantin and Hotho, Andreas}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, keywords = {author:PFISTER}, month = {06}, pages = {816-825}, title = {Self-Supervised Multi-Task Pretraining Improves Image Aesthetic Assessment}, year = 2021 }

2020[ to top ]

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 ]
- [ Download ]
- [ BibSonomy-Post ]
@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 }

Bildnachweise