Fabian David Schmidt
Fabian David Schmidt
Research associate / Doctoral student
WüNLP (LS Informatik XII)
Julius-Maximilians-Universität
John-Skilton-Str. 8a
John-Skilton-Str. 8a
97074
Würzburg
Building:
Sensalight (SK8)
Room:
03.003
I am a Ph.D. candidate at WüNLP and work on topics of multilingual representation learning and sample-efficient cross-lingual transfer. I am co-advised by Prof. Dr. Goran Glavaš and Ivan Vulić from the University of Cambridge.
- Machine Learning & Deep Learning
- Representation Learning for Multilingual & Low-Resource Cross-Lingual NLP
- Cross-Lingual Lexical and Distributional Semantics
- Information Retrieval
Papers
- Fabian David Schmidt, Ivan Vulić, Goran Glavaš. Free Lunch: Robust Cross-Lingual Transfer via Model Checkpoint Averaging, In Proceedings of the Annual Meeting of the Association for Computational Linguistics, Toronto, 2023.
- Fabian David Schmidt, Ivan Vulić, Goran Glavaš. Don't Stop Fine-Tuning: On Training Regimes for Few-Shot Cross-Lingual Transfer with Multilingual Language Models, In Proceedings of the Conference on Empirical Methods in Natural Language Processing: Main Conference, forthcoming, Abu Dhabi, 2022.
- Fabian David Schmidt, Ivan Vulić, Goran Glavaš. SLICER: Sliced Fine-Tuning for Low-Resource Cross-Lingual Transfer for Named Entity Recognition, In Proceedings of the Conference on Empirical Methods in Natural Language Processing: Main Conference, Abu Dhabi, 2022.
System Demonstrations
- Fabian David Schmidt, Markus Dietsche, Simone Ponzetto, Goran Glavaš. SEAGLE: A Platform for Comparative Evaluation of Semantic Encoders for Information Retrieval, In Proceedings of the Conference on Empirical Methods in Natural Language Processing: System Demonstrations. pages 199–204, Hong Kong, 2019.