Multi-head attention graph convolutional network model:End-to-end entity and relation joint extraction based on multi-head attention graph convolutional network  

作　　者：Zhihua Tao Chunping Ouyang Yongbin Liu Tonglee Chung Yixin Cao 

机构地区：[1]School of Computer Science,University of South China,Hengyang,China [2]Department of Computer Science and technology,Tsinghua University,Beijing,China [3]School of Computer and Information Systems,Singapore Management University,Singapore,Singapore

出　　处：《CAAI Transactions on Intelligence Technology》2023年第2期468-477,共10页智能技术学报（英文）

基　　金：State Key Program of National Natural Science of China,Grant/Award Number:61533018;National Natural Science Foundation of China,Grant/Award Number:61402220;Philosophy and Social Science Foundation of Hunan Province,Grant/Award Number:16YBA323;Natural Science Foundation of Hunan Province,Grant/Award Number:2020JJ4525;Scientific Research Fund of Hunan Provincial Education Department,Grant/Award Numbers:18B279,19A439。

摘　　要：At present,the entity and relation joint extraction task has attracted more and more scholars'attention in the field of natural language processing(NLP).However,most of their methods rely on NLP tools to construct dependency trees to obtain sentence structure information.The adjacency matrix constructed by the dependency tree can convey syntactic information.Dependency trees obtained through NLP tools are too dependent on the tools and may not be very accurate in contextual semantic description.At the same time,a large amount of irrelevant information will cause redundancy.This paper presents a novel end-to-end entity and relation joint extraction based on the multihead attention graph convolutional network model(MAGCN),which does not rely on external tools.MAGCN generates an adjacency matrix through a multi-head attention mechanism to form an attention graph convolutional network model,uses head selection to identify multiple relations,and effectively improve the prediction result of overlapping relations.The authors extensively experiment and prove the method's effectiveness on three public datasets:NYT,WebNLG,and CoNLL04.The results show that the authors’method outperforms the state-of-the-art research results for the task of entities and relation extraction.

关 键 词：information retrieval natural language processing 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]