Discriminative Reasoning with Sparse Event Representation for Document-level Event-Event Relation Extraction

Changsen Yuan, Heyan Huang, Yixin Cao, Yonggang Wen


Abstract
Document-level Event Causality Identification (DECI) aims to extract causal relations between events in a document. It challenges conventional sentence-level task (SECI) with difficult long-text understanding. In this paper, we propose a novel DECI model (SENDIR) for better document-level reasoning. Different from existing works that build an event graph via linguistic tools, SENDIR does not require any prior knowledge. The basic idea is to discriminate event pairs in the same sentence or span multiple sentences by assuming their different information density: 1) low density in the document suggests sparse attention to skip irrelevant information. Our module 1 designs various types of attention for event representation learning to capture long-distance dependence. 2) High density in a sentence makes SECI relatively easy. Module 2 uses different weights to highlight the roles and contributions of intra- and inter-sentential reasoning, which introduces supportive event pairs for joint modeling. Extensive experiments demonstrate great improvements in SENDIR and the effectiveness of various sparse attention for document-level representations. Codes will be released later.
Anthology ID:
2023.acl-long.897
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16222–16234
Language:
URL:
https://aclanthology.org/2023.acl-long.897
DOI:
10.18653/v1/2023.acl-long.897
Bibkey:
Cite (ACL):
Changsen Yuan, Heyan Huang, Yixin Cao, and Yonggang Wen. 2023. Discriminative Reasoning with Sparse Event Representation for Document-level Event-Event Relation Extraction. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 16222–16234, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Discriminative Reasoning with Sparse Event Representation for Document-level Event-Event Relation Extraction (Yuan et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.897.pdf
Video:
 https://aclanthology.org/2023.acl-long.897.mp4