What Has LeBenchmark Learnt about French Syntax?

Zdravko Dugonjić, Adrien Pupier, Benjamin Lecouteux, Maximin Coavoux

Abstract
The paper reports on a series of experiments aiming at probing LeBenchmark, a pretrained acoustic model trained on 7k hours of spoken French, for syntactic information. Pretrained acoustic models are increasingly used for downstream speech tasks such as automatic speech recognition, speech translation, spoken language understanding or speech parsing. They are trained on very low level information (the raw speech signal), and do not have explicit lexical knowledge. Despite that, they obtained reasonable results on tasks that requires higher level linguistic knowledge. As a result, an emerging question is whether these models encode syntactic information. We probe each representation layer of LeBenchmark for syntax, using the Orféo treebank, and observe that it has learnt some syntactic information. Our results show that syntactic information is more easily extractable from the middle layers of the network, after which a very sharp decrease is observed.
Anthology ID:
2024.lrec-main.1521
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
17493–17499
Language:
URL:
https://aclanthology.org/2024.lrec-main.1521
DOI:
Bibkey:
Cite (ACL):
Zdravko Dugonjić, Adrien Pupier, Benjamin Lecouteux, and Maximin Coavoux. 2024. What Has LeBenchmark Learnt about French Syntax?. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 17493–17499, Torino, Italia. ELRA and ICCL.
Cite (Informal):
What Has LeBenchmark Learnt about French Syntax? (Dugonjić et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2024.lrec-main.1521.pdf
PDF Search