Exploring Soft-Label Training for Implicit Discourse Relation Recognition

Nelson Filipe Costa, Leila Kosseim


Abstract
This paper proposes a classification model for single label implicit discourse relation recognition trained on soft-label distributions. It follows the PDTB 3.0 framework and it was trained and tested on the DiscoGeM corpus, where it achieves an F1-score of 51.38 on third-level sense classification of implicit discourse relations. We argue that training on soft-label distributions allows the model to better discern between more ambiguous discourse relations.
Anthology ID:
2024.codi-1.11
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:
120–126
Language:
URL:
https://aclanthology.org/2024.codi-1.11
DOI:
Bibkey:
Cite (ACL):
Nelson Filipe Costa and Leila Kosseim. 2024. Exploring Soft-Label Training for Implicit Discourse Relation Recognition. In Proceedings of the 5th Workshop on Computational Approaches to Discourse (CODI 2024), pages 120–126, St. Julians, Malta. Association for Computational Linguistics.
Cite (Informal):
Exploring Soft-Label Training for Implicit Discourse Relation Recognition (Costa & Kosseim, CODI-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.codi-1.11.pdf
Video:
 https://aclanthology.org/2024.codi-1.11.mp4