What Causes the Failure of Explicit to Implicit Discourse Relation Recognition?

Wei Liu, Stephen Wan, Michael Strube


Abstract
We consider an unanswered question in the discourse processing community: why do relation classifiers trained on explicit examples (with connectives removed) perform poorly in real implicit scenarios? Prior work claimed this is due to linguistic dissimilarity between explicit and implicit examples but provided no empirical evidence. In this study, we show that one cause for such failure is a label shift after connectives are eliminated. Specifically, we find that the discourse relations expressed by some explicit instances will change when connectives disappear. Unlike previous work manually analyzing a few examples, we present empirical evidence at the corpus level to prove the existence of such shift. Then, we analyze why label shift occurs by considering factors such as the syntactic role played by connectives, ambiguity of connectives, and more. Finally, we investigate two strategies to mitigate the label shift: filtering out noisy data and joint learning with connectives. Experiments on PDTB 2.0, PDTB 3.0, and the GUM dataset demonstrate that classifiers trained with our strategies outperform strong baselines.
Anthology ID:
2024.naacl-long.150
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2738–2753
Language:
URL:
https://aclanthology.org/2024.naacl-long.150
DOI:
Bibkey:
Cite (ACL):
Wei Liu, Stephen Wan, and Michael Strube. 2024. What Causes the Failure of Explicit to Implicit Discourse Relation Recognition?. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 2738–2753, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
What Causes the Failure of Explicit to Implicit Discourse Relation Recognition? (Liu et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.150.pdf
Copyright:
 2024.naacl-long.150.copyright.pdf