Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2023

Abstract

Document-level Event-Event Relation Extraction (DERE) aims to extract relations between events in a document. It challenges conventional sentence-level task (SERE) with difficult long-text understanding. In this paper, we propose a novel DERE 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 SERE 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. © 2023 Association for Computational Linguistics.

Keywords

Event graphs, Event representations, Extraction modeling; Information density, Joint models, Lower density, Prior-knowledge, Relation extraction, Sentence level

Discipline

Databases and Information Systems

Research Areas

Data Science and Engineering; Information Systems and Management

Publication

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023, Toronto, Canada, July 9-14

Volume

1

First Page

16222

Last Page

16234

ISBN

9781959429722

Publisher

ACL

City or Country

Texas

Share

COinS