典型文献
Event Temporal Relation Extraction with Attention Mechanism and Graph Neural Network
文献摘要：
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.
文献关键词：
中图分类号：
作者姓名：
Xiaoliang Xu;Tong Gao;Yuxiang Wang;Xinle Xuan
作者机构：
Department of Computer Science and Engineering,Hangzhou Dianzi University,Hangzhou 310018,China;Hangzhou Sanhui Digital Information Technology Co.,Ltd,Hangzhou 310018,China
文献出处：
引用格式：
[1]Xiaoliang Xu;Tong Gao;Yuxiang Wang;Xinle Xuan-.Event Temporal Relation Extraction with Attention Mechanism and Graph Neural Network)[J].清华大学学报自然科学版（英文版）,2022(01):79-90
A类：
TimeBank
B类：
Event,Temporal,Relation,Extraction,Attention,Mechanism,Graph,Neural,Network,temporal,extraction,important,part,natural,language,processing,Many,models,being,used,this,task,development,deep,learning,However,most,existing,methods,cannot,accurately,degree,association,between,different,tokens,events,related,information,effectively,integrated,In,paper,integration,that,integrates,through,multilayer,bidirectional,long,short,term,memory,Bi,attention,Although,above,scheme,improve,performance,still,further,optimized,To,previous,novel,relational,graph,network,incorporates,attributes,approach,first,build,semantic,dependency,parsing,considers,edges,by,using,top,mechanisms,hidden,contextual,representations,finally,predict,relations,We,evaluate,proposed,Dense,dataset,Compared,baselines,Micro,scores,obtained,our,respectively
AB值：
0.607167
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
