I am a final year PhD student at the University of Würzburg, Germany, and advised by Goran Glavaš (University of Würzburg) and Ivan Vulić (University of Cambridge). I am interested in robust and scalable cross-lingual transfer in the field of Natural Language Processing. Before that, I obtained my B.Sc. in Finance and interned at Goldman Sachs in London. Next to my research, I sometimes contribute to open source projects like telescope.nvim. You can find more info on my CV.
News
Jan, 2024 | I started my 4-month internship at NEC Laboratories Europe with Chia-Chien Hung and Carolin Lawrence. |
Oct, 2023 | Our paper "One For All & All For One: Bypassing Hyperparameter Tuning with Model Averaging for Cross-Lingual Transfer" was accepted to Findings of EMNLP! |
Sep, 2023 | I gave an invited talk about my work on robust and scalable cross-lingual transfer at the Language Science and Technology department of Uni Saarland. |
Publications
One For All & All For One: Bypassing Hyperparameter Tuning with Model Averaging for Cross-Lingual Transfer Fabian David Schmidt, Ivan Vulić, Goran Glavaš. Findings of the 2023 Conference on Empirical Methods in Natural Language Processing |
Free Lunch: Robust Cross-Lingual Transfer via Model Checkpoint Averaging Fabian David Schmidt, Ivan Vulić, Goran Glavaš. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics |
Don’t Stop Fine-Tuning: On Training Regimes for Few-Shot Cross-Lingual Transfer with Multilingual Language Models Fabian David Schmidt, Ivan Vulić, Goran Glavaš. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing |
SLICER: Sliced Fine-Tuning for Low-Resource Cross-Lingual Transfer for Named Entity Recognition Fabian David Schmidt, Ivan Vulić, Goran Glavaš. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing |
SEAGLE: A Platform for Comparative Evaluation of Semantic Encoders for Information Retrieval Fabian David Schmidt, Markus Dietsche, Simone Paolo Ponzetto, Goran Glavaš. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing: System Demonstrations |