Thomas Gerald

Associate Professor at LISN, CNRS

Université Paris Saclay

Contact:

thomas[dot]gerald[at]universite-paris-saclay[dot]fr

Thomas Gerald is an associate professor at Université Paris Saclay, in the CNRS/LISN research laboratory since September 2023

His research include Deep-Learning architectures for NLP and Information retrieval and its application for Question-Answering and explainable AI.

LatestPublications:

Pierre Lepagnol, Sahar Ghannay, Thomas Gerald, Christophe Servan, and Sophie Rosset. Leveraging information retrieval to enhance spoken language understanding prompts in few-shot learning. In Odette Scharenborg, Catharine Oertel, and Khiet Truong, editors, 26th Annual Conference of the International Speech Communication Association, Interspeech 2025, Rotterdam, The Netherlands, 17-21 August 2025. ISCA, 2025. URL: https://doi.org/10.21437/Interspeech.2025-175, doi:10.21437/INTERSPEECH.2025-175.
Pierre Lepagnol, Sahar Ghannay, Thomas Gerald, Christophe Servan, and Sophie Rosset. Leveraging information retrieval to enhance spoken language understanding prompts in few-shot learning. CoRR, 2025. URL: https://doi.org/10.48550/arXiv.2506.03035, arXiv:2506.03035, doi:10.48550/ARXIV.2506.03035.
Thomas Gerald, Louis Tamames, Sofiane Ettayeb, Ha-Quang Le, Patrick Paroubek, and Anne Vilnat. Cquae: A new contextualized question answering corpus on education domain. Data Knowl. Eng., 151:102305, 2024. URL: https://doi.org/10.1016/j.datak.2024.102305, doi:10.1016/J.DATAK.2024.102305.
Thomas Gerald, Anne Vilnat, Sofiane Ettayeb, Louis Tamames, and Patrick Paroubek. Introducing cquae : A new french contextualised question-answering corpus for the education domain. In Nicoletta Calzolari, Min-Yen Kan, Véronique Hoste, Alessandro Lenci, Sakriani Sakti, and Nianwen Xue, editors, Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC/COLING 2024, 20-25 May, 2024, Torino, Italy, 9234–9244. ELRA and ICCL, 2024. URL: https://aclanthology.org/2024.lrec-main.808.
Pierre Lepagnol, Thomas Gerald, Sahar Ghannay, Christophe Servan, and Sophie Rosset. Small language models are good too: an empirical study of zero-shot classification. In Nicoletta Calzolari, Min-Yen Kan, Véronique Hoste, Alessandro Lenci, Sakriani Sakti, and Nianwen Xue, editors, Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC/COLING 2024, 20-25 May, 2024, Torino, Italy, 14923–14936. ELRA and ICCL, 2024. URL: https://aclanthology.org/2024.lrec-main.1299.
Thomas Gerald, Louis Tamames, Sofiane Ettayeb, Patrick Paroubek, and Anne Vilnat. Cquae : un nouveau corpus de question-réponse pour l'enseignement. In Mathieu Balaguer, Nihed Bendahman, Lydia-Mai Ho-Dac, Julie Mauclair, José G. Moreno, and Julien Pinquier, editors, Actes de la 31ème Conférence sur le Traitement Automatique des Langues Naturelles, TALN 2024 - Volume 1 : articles longs et prises de position, Toulouse, France, July 8-12, 2024, 50–63. ATALA and AFPC, 2024. URL: https://aclanthology.org/2024.jeptalnrecital-taln.4.