基于多数据源的知识图谱构建方法研究
|
摘要
针对多数据源的融合应用,构建了基于多数据源的知识图谱.首先,对不同领域内的数据源构建相应本体库,并将不同本体库通过数据融合映射到全局本体库;然后,利用实体对齐和实体链接方法进行知识获取和融合;最后,搭建知识图谱应用平台,提供查询和统计等操作.在实体对齐方面,利用传统的基于相似性传播实体对齐方法,获得良好的实体对齐效果;在实体链接方面,提出了基于约束嵌入转换的预测推理方法,实验结果表明,在预测准确率上取得较好的结果.
To improve the application of multi-source data fusion,this study constructs a knowledge graph-based data fusion model. This model firstly constructed corresponding domain ontology for each special field,and then consolidated all domain ontology into a global ontology. After that,it retrieved and fused knowledge from the global ontology by entity alignment and linking methods. At last it built an application platform of knowledge graph with friendly interfaces to execute query and statistics,etc.Besides that,this model improved the result of entity aligning by adopting traditional similarity detection approach. And experiment results also demonstrated its good prediction accuracy by proposing a constraint based embedding model in entity linking process.
To improve the application of multi-source data fusion,this study constructs a knowledge graph-based data fusion model. This model firstly constructed corresponding domain ontology for each special field,and then consolidated all domain ontology into a global ontology. After that,it retrieved and fused knowledge from the global ontology by entity alignment and linking methods. At last it built an application platform of knowledge graph with friendly interfaces to execute query and statistics,etc.Besides that,this model improved the result of entity aligning by adopting traditional similarity detection approach. And experiment results also demonstrated its good prediction accuracy by proposing a constraint based embedding model in entity linking process.
引文
[1]PUJARA J,MIAO H,GETOOR L,et al.Knowledge graph identification[C]//International Semantic Web Conference.Berlin:Springer,2013:542-557.
[2]刘峤,李杨,段宏,等.知识图谱构建技术综述[J].计算机研究与发展,2016,53(3):582-600.
[3]肖仰华,张可尊,汪卫.一种面向图书的阅读领域知识图谱构建方法:103488724A[P].2014-01-01.
[4]金贵阳,吕福在,项占琴.基于知识图谱和语义网技术的企业信息集成方法[J].东南大学学报(自然科学版),2014,44(2):250-255.
[5]胡芳槐.基于多种数据源的中文知识图谱构建方法研究[D].上海:华东理工大学,2015.
[6]王巍巍,王志刚,潘亮铭,等.双语影视知识图谱的构建研究[J].北京大学学报(自然科学版),2016,52(1):25-34.
[7]鄂世嘉,林培裕,向阳.自动化构建的中文知识图谱系统[J].计算机应用,2016,36(4):992-996.
[8]吴运兵,杨帆,赖国华,等.知识图谱学习和推理研究进展[J].小型微型计算机系统,2016,37(9):2 007-2 013.
[9]庄严,李国良,冯建华.知识库实体对齐技术综述[J].计算机研究与发展,2016,53(1):165-192.
[10]徐增林,盛泳潘,贺丽荣,等.知识图谱技术综述[J].电子科技大学学报,2016,45(4):589-606.
[11]LACOSTE-JULIEN S,PALLA K,DAVIES A,et al.SIGMa:simple greedy matching for aligning large knowledge bases[C]//Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM,2013:572-580.
[12]刘峤,钟云,李杨,等.基于图的中文集成实体链接算法[J].计算机研究与发展,2016,53(2):270-283.
[13]SHEN W,WANG J,HAN J.Entity linking with a knowledge base:issues,techniques,and solutions[J].IEEE Transactions on Knowledge and Data Engineering,2015,27(2):443-460.
[14]LI Y,WANG C,HAN F,et al.Mining evidences for named entity disambiguation[C]//Proceedings of the 19th ACM SIGK-DD International Conference on Knowledge Discovery and Data Mining.New York:ACM,2013:1 070-1 078.
[15]NICKEL M,MURPHY K,TRESP V,et al.A review of relational machine learning for knowledge graphs[J].Proceedings of the IEEE,2016,104(1):11-33.
[16]刘知远,孙茂松,林衍凯,等.知识表示学习研究进展[J].计算机研究与发展,2016,53(2):247-261.
[17]刘康,张元哲,纪国良,等.基于表示学习的知识库问答研究进展与展望[J].自动化学报,2016,42(6):807-818.
[18]BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[C]//Advances in Neural Information Processing Systems.Nevada:[s.n.],2013:2 787-2 795.
[2]刘峤,李杨,段宏,等.知识图谱构建技术综述[J].计算机研究与发展,2016,53(3):582-600.
[3]肖仰华,张可尊,汪卫.一种面向图书的阅读领域知识图谱构建方法:103488724A[P].2014-01-01.
[4]金贵阳,吕福在,项占琴.基于知识图谱和语义网技术的企业信息集成方法[J].东南大学学报(自然科学版),2014,44(2):250-255.
[5]胡芳槐.基于多种数据源的中文知识图谱构建方法研究[D].上海:华东理工大学,2015.
[6]王巍巍,王志刚,潘亮铭,等.双语影视知识图谱的构建研究[J].北京大学学报(自然科学版),2016,52(1):25-34.
[7]鄂世嘉,林培裕,向阳.自动化构建的中文知识图谱系统[J].计算机应用,2016,36(4):992-996.
[8]吴运兵,杨帆,赖国华,等.知识图谱学习和推理研究进展[J].小型微型计算机系统,2016,37(9):2 007-2 013.
[9]庄严,李国良,冯建华.知识库实体对齐技术综述[J].计算机研究与发展,2016,53(1):165-192.
[10]徐增林,盛泳潘,贺丽荣,等.知识图谱技术综述[J].电子科技大学学报,2016,45(4):589-606.
[11]LACOSTE-JULIEN S,PALLA K,DAVIES A,et al.SIGMa:simple greedy matching for aligning large knowledge bases[C]//Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM,2013:572-580.
[12]刘峤,钟云,李杨,等.基于图的中文集成实体链接算法[J].计算机研究与发展,2016,53(2):270-283.
[13]SHEN W,WANG J,HAN J.Entity linking with a knowledge base:issues,techniques,and solutions[J].IEEE Transactions on Knowledge and Data Engineering,2015,27(2):443-460.
[14]LI Y,WANG C,HAN F,et al.Mining evidences for named entity disambiguation[C]//Proceedings of the 19th ACM SIGK-DD International Conference on Knowledge Discovery and Data Mining.New York:ACM,2013:1 070-1 078.
[15]NICKEL M,MURPHY K,TRESP V,et al.A review of relational machine learning for knowledge graphs[J].Proceedings of the IEEE,2016,104(1):11-33.
[16]刘知远,孙茂松,林衍凯,等.知识表示学习研究进展[J].计算机研究与发展,2016,53(2):247-261.
[17]刘康,张元哲,纪国良,等.基于表示学习的知识库问答研究进展与展望[J].自动化学报,2016,42(6):807-818.
[18]BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[C]//Advances in Neural Information Processing Systems.Nevada:[s.n.],2013:2 787-2 795.