Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

10-2022

Abstract

Document-level Event Causality Identification (DECI) aims to identify event-event causal relations in a document. Existing works usually build an event graph for global reasoning across multiple sentences. However, the edges between events have to be carefully designed through heuristic rules or external tools. In this paper, we propose a novel Event Relational Graph TransfOrmer (ERGO) framework1 for DECI, to ease the graph construction and improve it over the noisy edge issue. Different from conventional event graphs, we define a pair of events as a node and build a complete event relational graph without any prior knowledge or tools. This naturally formulates DECI as a node classification problem, and thus we capture the causation transitivity among event pairs via a graph transformer. Furthermore, we design a criss-cross constraint and an adaptive focal loss for the imbalanced classification, to alleviate the issues of false positives and false negatives. Extensive experiments on two benchmark datasets show that ERGO greatly outperforms previous state-of-the-art (SOTA) methods (12.8% F1 gains on average).

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces

Research Areas

Data Science and Engineering

Publication

Proceedings of the 29th International Conference on Computational Linguistics, Gyeongju, South Korea, 2022 October 12-17

First Page

2118

Last Page

2128

Publisher

Association for Computational Linguistics

City or Country

Gyeongju, South Korea

Additional URL

https://aclanthology.org/2022.coling-1.185

Share

COinS