Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech
Adrien Pupier, Maximin Coavoux, Jérôme Goulian, Benjamin Lecouteux
Abstract
Direct dependency parsing of the speech signal –as opposed to parsing speech transcriptions– has recently been proposed as a task (Pupier et al. 2022), as a way of incorporating prosodic information in the parsing system and bypassing the limitations of a pipeline approach that would consist of using first an Automatic Speech Recognition (ASR) system and then a syntactic parser. In this article, we report on a set of experiments aiming at assessing the performance of two parsing paradigms (graph-based parsing and sequence labeling based parsing) on speech parsing. We perform this evaluation on a large treebank of spoken French, featuring realistic spontaneous conversations. Our findings show that (i) the graph based approach obtain better results across the board (ii) parsing directly from speech outperforms a pipeline approach, despite having 30% fewer parameters.- Anthology ID:
- 2024.acl-short.22
- Volume:
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 225–233
- Language:
- URL:
- https://aclanthology.org/2024.acl-short.22
- DOI:
- Cite (ACL):
- Adrien Pupier, Maximin Coavoux, Jérôme Goulian, and Benjamin Lecouteux. 2024. Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 225–233, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech (Pupier et al., ACL 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.acl-short.22.pdf