Discrete Argument Representation Learning for Interactive Argument Pair Identification

Lu Ji, Zhongyu Wei, Jing Li, Qi Zhang, Xuanjing Huang


Abstract
In this paper, we focus on identifying interactive argument pairs from two posts with opposite stances to a certain topic. Considering opinions are exchanged from different perspectives of the discussing topic, we study the discrete representations for arguments to capture varying aspects in argumentation languages (e.g., the debate focus and the participant behavior). Moreover, we utilize hierarchical structure to model post-wise information incorporating contextual knowledge. Experimental results on the large-scale dataset collected from CMV show that our proposed framework can significantly outperform the competitive baselines. Further analyses reveal why our model yields superior performance and prove the usefulness of our learned representations.
Anthology ID:
2021.naacl-main.431
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5467–5478
Language:
URL:
https://aclanthology.org/2021.naacl-main.431
DOI:
10.18653/v1/2021.naacl-main.431
Bibkey:
Cite (ACL):
Lu Ji, Zhongyu Wei, Jing Li, Qi Zhang, and Xuanjing Huang. 2021. Discrete Argument Representation Learning for Interactive Argument Pair Identification. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5467–5478, Online. Association for Computational Linguistics.
Cite (Informal):
Discrete Argument Representation Learning for Interactive Argument Pair Identification (Ji et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.431.pdf
Video:
 https://aclanthology.org/2021.naacl-main.431.mp4