Label-Aware Chinese Event Detection with Heterogeneous Graph Attention Network

Event detection (ED) seeks to recognize event triggers and classify them into the predefined event types. Chinese ED is formulated as a character-level task owing to the uncertain word boundaries. Prior methods try to incorporate word-level information into characters to enhance their semantics. How...

Full description

Saved in:
Bibliographic Details
Published in:Journal of computer science and technology 2024-02, Vol.39 (1), p.227-242
Main Authors: Cui, Shi-Yao, Yu, Bo-Wen, Cong, Xin, Liu, Ting-Wen, Tan, Qing-Feng, Shi, Jin-Qiao
Format: Article
Language:English
Subjects:
Artificial Intelligence
Competition
Computer Science
Data Structures and Information Theory
Detection
Embedding
Heterogeneity
Information Systems Applications (incl.Internet)
Labels
Regular Paper
Semantics
Software Engineering
Theory of Computation
Word boundaries
Words (language)
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Event detection (ED) seeks to recognize event triggers and classify them into the predefined event types. Chinese ED is formulated as a character-level task owing to the uncertain word boundaries. Prior methods try to incorporate word-level information into characters to enhance their semantics. However, they experience two problems. First, they fail to incorporate word-level information into each character the word encompasses, causing the insufficient word-character interaction problem. Second, they struggle to distinguish events of similar types with limited annotated instances, which is called the event confusing problem. This paper proposes a novel model named Label-Aware Heterogeneous Graph Attention Network (L-HGAT) to address these two problems. Specifically, we first build a heterogeneous graph of two node types and three edge types to maximally preserve word-character interactions, and then deploy a heterogeneous graph attention network to enhance the semantic propagation between characters and words. Furthermore, we design a pushing-away game to enlarge the predicting gap between the ground-truth event type and its confusing counterpart for each character. Experimental results show that our L-HGAT model consistently achieves superior performance over prior competitive methods.
ISSN:1000-9000
1860-4749
DOI:10.1007/s11390-023-1541-6