Exploring Discourse Structures for Argument Impact Classification

Xin Liu, Jiefu Ou, Yangqiu Song, Xin Jiang


Abstract
Discourse relations among arguments reveal logical structures of a debate conversation. However, no prior work has explicitly studied how the sequence of discourse relations influence a claim’s impact. This paper empirically shows that the discourse relations between two arguments along the context path are essential factors for identifying the persuasive power of an argument. We further propose DisCOC to inject and fuse the sentence-level structural discourse information with contextualized features derived from large-scale language models. Experimental results and extensive analysis show that the attention and gate mechanisms that explicitly model contexts and texts can indeed help the argument impact classification task defined by Durmus et al. (2019), and discourse structures among the context path of the claim to be classified can further boost the performance.
Anthology ID:
2021.acl-long.306
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3958–3969
Language:
URL:
https://aclanthology.org/2021.acl-long.306
DOI:
10.18653/v1/2021.acl-long.306
Bibkey:
Cite (ACL):
Xin Liu, Jiefu Ou, Yangqiu Song, and Xin Jiang. 2021. Exploring Discourse Structures for Argument Impact Classification. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3958–3969, Online. Association for Computational Linguistics.
Cite (Informal):
Exploring Discourse Structures for Argument Impact Classification (Liu et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.306.pdf
Video:
 https://aclanthology.org/2021.acl-long.306.mp4
Code
 HKUST-KnowComp/DisCOC