典型文献
MHGCN:Multiview Highway Graph Convolutional Network for Cross-Lingual Entity Alignment
文献摘要：
Knowledge graphs(KGs)provide a wealth of prior knowledge for the research on social networks.Cross-lingual entity alignment aims at integrating complementary KGs from different languages and thus benefits various knowledge-driven social network studies.Recent entity alignment methods often take an embedding-based approach to model the entity and relation embedding of KGs.However,these studies mostly focus on the information of the entity itself and its structural features but ignore the influence of multiple types of data in KGs.In this paper,we propose a new embedding-based framework named multiview highway graph convolutional network(MHGCN),which considers the entity alignment from the views of entity semantic,relation semantic,and entity attribute.To learn the structural features of an entity,the MHGCN employs a highway graph convolutional network(GCN)for entity embedding in each view.In addition,the MHGCN weights and fuses the multiple views according to the importance of the embedding from each view to obtain a better entity embedding.The alignment entities are identified based on the similarity of entity embeddings.The experimental results show that the MHGCN consistently outperforms the state-of-the-art alignment methods.The research also will benefit knowledge fusion through cross-lingual KG entity alignment.
文献关键词：
中图分类号：
作者姓名：
Jianliang Gao;Xiangyue Liu;Yibo Chen;Fan Xiong
作者机构：
School of Computer Science and Engineering,Central South University,Changsha 410083,China;Information and Communication Branch,State Grid Hunan Electric Power Company Limited,Changsha 410004,China
文献出处：
引用格式：
[1]Jianliang Gao;Xiangyue Liu;Yibo Chen;Fan Xiong-.MHGCN:Multiview Highway Graph Convolutional Network for Cross-Lingual Entity Alignment)[J].清华大学学报自然科学版（英文版）,2022(04):719-728
A类：
MHGCN,Multiview,Lingual
B类：
Highway,Graph,Convolutional,Network,Cross,Entity,Alignment,Knowledge,graphs,KGs,provide,wealth,prior,knowledge,research,social,networks,lingual,entity,alignment,aims,integrating,complementary,from,different,languages,thus,benefits,various,driven,studies,Recent,methods,often,take,approach,model,relation,However,these,mostly,focus,information,itself,structural,features,ignore,influence,multiple,types,data,In,this,paper,propose,new,framework,named,multiview,highway,convolutional,which,considers,views,semantic,attribute,To,learn,employs,each,addition,weights,fuses,according,importance,obtain,better,entities,are,identified,similarity,embeddings,experimental,results,show,that,consistently,outperforms,state,art,also,will,fusion,through,cross
AB值：
0.483849
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。
