Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2023

Abstract

Document-level Event Causality Identification (DECI) aims to recognize causal relations between events within a document. Recent studies focus on building a document-level graph for cross-sentence reasoning, but ignore important causal structures — there are one or two “central” events that prevail throughout the document, with most other events serving as either their cause or consequence. In this paper, we manually annotate central events for a systematical investigation and propose a novel DECI model, CHEER, which performs high-order reasoning while considering event centrality. First, we summarize a general GNN-based DECI model and provide a unified view for better understanding. Second, we design an Event Interaction Graph (EIG) involving the interactions among events (e.g., coreference) and event pairs, e.g., causal transitivity, cause(A, B) AND cause(B, C) → cause(A, C). Finally, we incorporate event centrality information into the EIG reasoning network via well-designed features and multi-task learning. We have conducted extensive experiments on two benchmark datasets. The results present great improvements (5.9% F1 gains on average) and demonstrate the effectiveness of each main component.

Keywords

benchmark datasets; causal relations; coreference; high-order; higher-order; identification modeling; interaction graphs; level graphs; multitask learning; ordering events

Discipline

Computer Sciences | OS and Networks

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of The 61st Annual Meeting of the Association for Computational Linguistics

Volume

Volume 1: Long Papers

First Page

10804

Last Page

10816

Identifier

10.18653/v1/2023.acl-long.604

Publisher

ACM

City or Country

Canada

Additional URL

https://doi.org/10.18653/v1/2023.acl-long.604

Share

COinS