Dr. Sabine Weber

Dr. Sabine Weber is a postdoctoral researcher at the Bamberg NLP Group, specializing in domain adaptation, multilinguality and robustness. They earned their Ph.D. in Computer Science from the University on Edinburgh, focusing on multilingual entailment detection, language adaptation and knowledge graphs. Before that they received a B.Sc. and a M.Sc. in Computer Engineering from the TU Berlin, and a B.A. in Slavic Languages from the Humboldt University Berlin. 

In addition to building models that are more robust and flexible, they are interested in making NLP models more explainable and examining the societal impact of NLP.  They are also a core organizer for the volunteer-run organization Queer in AI. 

 

Publications: here 

Publications

Li, Tianyi et al. (2022a): Language Models Are Poor Learners of Directional Inference. In: Findings of the Association for Computational Linguistics: EMNLP 2022. Association for Computational Linguistics. S. 903–921.

Li, Tianyi et al. (2022b): Cross-lingual Inference with A Chinese Entailment Graph. In: Findings of the Association for Computational Linguistics: ACL 2022. Association for Computational Linguistics. S. 1214–1233.

Weber, Sabine/Steedman, Mark (2021a): Zero-Shot Cross-Lingual Transfer is a Hard Baseline to Beat in German Fine-Grained Entity Typing. In: Proceedings of the Second Workshop on Insights from Negative Results in NLP. Association for Computational Linguistics. S. 42–48.

Weber, Sabine/Steedman, Mark (2021b): Fine-grained General Entity Typing in German using GermaNet. In: Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15). Association for Computational Linguistics. S. 138–143.

Weber, Sabine/Steedman, Mark (2019): Construction and Alignment of Multilingual Entailment Graphs for Semantic Inference. In: Proceedings of the 2019 Workshop on Widening NLP. Association for Computational Linguistics. S. 77–79.

Fähndrich, Johannes/Weber, Sabine/Kanthak, Hannes (2018): A Marker Passing Approach to Winograd Schemas. In: Semantic technology: 8th joint international conference, JIST 2018, Awaji, Japan, November 26–28, 2018, proceedings. Cham, Switzerland: Springer International Publishing. S. 165–181.

Srivastava, Ankit et al. (2018): Different German and English Coreference Resolution Models for Multi-domain Content Curation Scenarios. In: Language Technologies for the Challenges of the Digital Age: 27th International Conference, GSCL 2017, Berlin, Germany, September 13-14, 2017, Proceedings. Springer International Publishing. S. 48–61.