Label-Aware Chinese Event Detection with Heterogeneous Graph Attention Network  

作　　者：崔诗尧 郁博文 从鑫 柳厅文 谭庆丰 时金桥 Shi-Yao Cui;Bo-Wen Yu;Xin Cong;Ting-Wen Liu;Qing-Feng Tan;Jin-Qiao Shi(Institute of Information Engineering,Chinese Academy of Sciences,Beijing 100190,China;School of Cyber Security,University of Chinese Academy of Sciences,Beijing 100049,China;Cyberspace Institute of Advanced Technology,Guangzhou University,Guangzhou 510006,China;School of Cyber Security,Beijing University of Posts and Telecommunications,Beijing 100088,China)

机构地区：[1]Institute of Information Engineering,Chinese Academy of Sciences,Beijing 100190,China [2]School of Cyber Security,University of Chinese Academy of Sciences,Beijing 100049,China [3]Cyberspace Institute of Advanced Technology,Guangzhou University,Guangzhou 510006,China [4]School of Cyber Security,Beijing University of Posts and Telecommunications,Beijing 100088,China

出　　处：《Journal of Computer Science & Technology》2024年第1期227-242,共16页计算机科学技术学报（英文版）

基　　金：This work was supported by the National Key Research and Development Program of China under Grant No.2021YFB3100600;the Youth Innovation Promotion Association of Chinese Academy of Sciences under Grant No.2021153;the State Key Program of National Natural Science Foundation of China under Grant No.U2336202.

摘　　要：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 incorpo-rate 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-charac-ter 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.

关 键 词：Chinese event detection heterogeneous graph attention network(HGAT) label embedding 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]