Event Temporal Relation Extraction with Attention Mechanism and Graph Neural Network

作     者：Xiaoliang Xu Tong Gao Yuxiang Wang Xinle Xuan Xiaoliang Xu;Tong Gao;Yuxiang Wang;Xinle Xuan

作者机构：the Department of Computer Science and EngineeringHangzhou Dianzi UniversityHangzhou 310018China the Hangzhou Sanhui Digital Information Technology Co.Ltd.Hangzhou 310018China 

出 版 物：《Tsinghua Science and Technology》 (清华大学学报（自然科学版（英文版）)

年 卷 期：2022年第27卷第1期

页      面：79-90页

核心收录：

学科分类：08[工学] 081104[工学-模式识别与智能系统] 081203[工学-计算机应用技术] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National key Research&Development Program of China(No.2017YFC0820503) the National Natural Science Foundation of China(No.62072149) the National Social Science Foundation of China(No.19ZDA348) the Primary Research&Development Plan of Zhejiang(No.2021C03156) the Public Welfare Research Program of Zhejiang(No.LGG19F020017)。 

主　　题：temporal relation extraction neural network attention mechanism graph attention network 

摘      要：Event temporal relation extraction is an important part of natural language processing.Many models are being used in this task with the development of deep learning.However,most of the existing methods cannot accurately obtain the degree of association between different tokens and events,and event-related information cannot be effectively integrated.In this paper,we propose an event information integration model that integrates event information through multilayer bidirectional long short-term memory(Bi-LSTM)and attention mechanism.Although the above scheme can improve the extraction performance,it can still be further optimized.To further improve the performance of the previous scheme,we propose a novel relational graph attention network that incorporates edge attributes.In this approach,we first build a semantic dependency graph through dependency parsing,model a semantic graph that considers the edges’attributes by using top-k attention mechanisms to learn hidden semantic contextual representations,and finally predict event temporal relations.We evaluate proposed models on the TimeBank-Dense dataset.Compared to previous baselines,the Micro-F1 scores obtained by our models improve by 3.9%and 14.5%,respectively.