Argument Pair Extraction via Attention-guided Multi-Layer Multi-Cross Encoding

Liying Cheng, Tianyu Wu, Lidong Bing, Luo Si


Abstract
Argument pair extraction (APE) is a research task for extracting arguments from two passages and identifying potential argument pairs. Prior research work treats this task as a sequence labeling problem and a binary classification problem on two passages that are directly concatenated together, which has a limitation of not fully utilizing the unique characteristics and inherent relations of two different passages. This paper proposes a novel attention-guided multi-layer multi-cross encoding scheme to address the challenges. The new model processes two passages with two individual sequence encoders and updates their representations using each other’s representations through attention. In addition, the pair prediction part is formulated as a table-filling problem by updating the representations of two sequences’ Cartesian product. Furthermore, an auxiliary attention loss is introduced to guide each argument to align to its paired argument. An extensive set of experiments show that the new model significantly improves the APE performance over several alternatives.
Anthology ID:
2021.acl-long.496
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:
6341–6353
Language:
URL:
https://aclanthology.org/2021.acl-long.496
DOI:
10.18653/v1/2021.acl-long.496
Bibkey:
Cite (ACL):
Liying Cheng, Tianyu Wu, Lidong Bing, and Luo Si. 2021. Argument Pair Extraction via Attention-guided Multi-Layer Multi-Cross Encoding. 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 6341–6353, Online. Association for Computational Linguistics.
Cite (Informal):
Argument Pair Extraction via Attention-guided Multi-Layer Multi-Cross Encoding (Cheng et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.496.pdf
Video:
 https://aclanthology.org/2021.acl-long.496.mp4
Code
 tianyuterry/mlmc
Data
RR