Uncovering Implicit Inferences for Improved Relational Argument Mining

Ameer Saadat-Yazdi, Jeff Z. Pan, Nadin Kokciyan


Abstract
Argument mining seeks to extract arguments and their structure from unstructured texts. Identifying relations between arguments (such as attack, support, and neutral) is a challenging task because two arguments may be related to each other via implicit inferences. This task often requires external commonsense knowledge to discover how one argument relates to another. State-of-the-art methods, however, rely on pre-defined knowledge graphs, and thus might not cover target argument pairs well. We introduce a new generative neuro-symbolic approach to finding inference chains that connect the argument pairs by making use of the Commonsense Transformer (COMET). We evaluate our approach on three datasets for both the two-label (attack/support) and three-label (attack/support/neutral) tasks. Our approach significantly outperforms the state-of-the-art, by 2-5% in F1 score, on all three datasets.
Anthology ID:
2023.eacl-main.182
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2484–2495
Language:
URL:
https://aclanthology.org/2023.eacl-main.182
DOI:
10.18653/v1/2023.eacl-main.182
Bibkey:
Cite (ACL):
Ameer Saadat-Yazdi, Jeff Z. Pan, and Nadin Kokciyan. 2023. Uncovering Implicit Inferences for Improved Relational Argument Mining. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2484–2495, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Uncovering Implicit Inferences for Improved Relational Argument Mining (Saadat-Yazdi et al., EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-main.182.pdf
Video:
 https://aclanthology.org/2023.eacl-main.182.mp4