Abstract
Discourse analysis plays a crucial role in Natural Language Processing, with discourse relation prediction arguably being the most difficult task in discourse parsing. Previous studies have generally focused on explicit or implicit discourse relation classification in monologues, leaving dialogue an under-explored domain. Facing the data scarcity issue, we propose to leverage self-training strategies based on a Transformer backbone. Moreover, we design the first semi-supervised pipeline that sequentially predicts discourse structures and relations. Using 50 examples, our relation prediction module achieves 58.4 in accuracy on the STAC corpus, close to supervised state-of-the-art. Full parsing results show notable improvements compared to the supervised models both in-domain (gaming) and cross-domain (technical chat), with better stability.- Anthology ID:
- 2024.codi-1.15
- Volume:
- Proceedings of the 5th Workshop on Computational Approaches to Discourse (CODI 2024)
- Month:
- March
- Year:
- 2024
- Address:
- St. Julians, Malta
- Editors:
- Michael Strube, Chloe Braud, Christian Hardmeier, Junyi Jessy Li, Sharid Loaiciga, Amir Zeldes, Chuyuan Li
- Venues:
- CODI | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 161–176
- Language:
- URL:
- https://aclanthology.org/2024.codi-1.15
- DOI:
- Cite (ACL):
- Chuyuan Li, Chloé Braud, Maxime Amblard, and Giuseppe Carenini. 2024. Discourse Relation Prediction and Discourse Parsing in Dialogues with Minimal Supervision. In Proceedings of the 5th Workshop on Computational Approaches to Discourse (CODI 2024), pages 161–176, St. Julians, Malta. Association for Computational Linguistics.
- Cite (Informal):
- Discourse Relation Prediction and Discourse Parsing in Dialogues with Minimal Supervision (Li et al., CODI-WS 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2024.codi-1.15.pdf