基于双向对齐与属性信息的跨语言实体对齐

doi:10.19678/j.issn.1000-3428.0060540

摘要/Abstract

摘要： 实体对齐表示在不同的知识图谱中查找引用相同现实身份的实体。目前主流的基于图嵌入的实体对齐方法中的对齐实体通常具有相似的属性，有效利用属性信息可提升实体对齐效果，同时由于不同知识图谱之间的知识分布差异，仅考虑单个方向的对齐预测会导致预测结果出现偏差。针对上述问题，提出一种改进的跨语言实体对齐方法。利用融合属性信息的双向对齐图卷积网络模型，将前馈神经网络编码实体对应的属性信息与初始的实体嵌入相结合，得到联合属性信息的实体表示，并使用双向对齐机制实现跨语言的实体对齐预测。在3个跨语言数据集上的实验结果表明，该方法通过融合更多的知识图谱信息增强了实体表示能力，并且利用双向对齐机制缓解了数据分布差异问题，相比基于图嵌入的实体对齐方法整体性能更优。

关键词: 实体对齐, 知识图谱, 属性信息, 双向对齐, 图卷积网络

Abstract: Entity alignment is to find the entities that refer to the same real identity in different knowledge graphs.The alignment entities in most of the existing graph embedding-based entity alignment methods share similar attributes, which means utilizing attribute information can improve entity alignment performance.At the same time, due to the knowledge distribution differences between different knowledge graphs, alignment prediction that considers only a single direction will lead to deviation in alignment results.In response to the above problems, this paper proposes an improved cross-language entity alignment method.The method uses a Bidirectional alignment Graph Convolutional Network model with Attribution information(BiGCN-A), and combines the attribute information corresponding to the coded entity with the initial entity embedding through a feed-forward neural network to obtain an entity representation of joint attribute information.A bidirectional alignment mechanism is also used to realize cross-language entity alignment prediction.Experimental results on three cross-language datasets show that the proposed method enhances the entity representation ability by fusing more knowledge graph information.It also uses a bidirectional alignment mechanism to alleviate the problem of data distribution differences.Compared with the entity alignment method based on graph embedding, the proposed method displays better overall performance.

Key words: entity alignment, knowledge graph, attribute information, bidirectional alignment, Graph Convolutional Network(GCN)

中图分类号:

TP391.1

车超, 刘迪. 基于双向对齐与属性信息的跨语言实体对齐[J]. 计算机工程, 2022, 48(3): 74-80.

CHE Chao, LIU Di. Cross-language Entity Alignment Based on Bidirectional Alignment and Attribute Information[J]. Computer Engineering, 2022, 48(3): 74-80.

http://www.ecice06.com/CN/Y2022/V48/I3/74

图/表 6

20220330200657

20220330200701

20220330200704

20220330200708

20220330200711

20220330200714

参考文献

[1] YANG B S, MITCHELL T.Leveraging knowledge bases in LSTMs for improving machine reading[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.Stroudsburg, USA:Association for Computational Linguistics, 2017:1436-1446.
[2] MOUSSALLEM D, WAUER M, NGOMO A C N.Machine translation using semantic web technologies:a survey[J].Journal of Web Semantics, 2018, 51:1-19.
[3] ZHANG F Z, YUAN N J, LIAN D F, et al.Collaborative knowledge base embedding for recommender systems[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York, USA:ACM Press, 2016:353-362.
[4] ZHANG Y Y, DAI H J, KOZAREVA Z, et al.Variational reasoning for question answering with knowledge graph[EB/OL].[2020-12-07].http://arxiv.org/abs/1709.04071v1.
[5] BIZER C, LEHMANN J, KOBILAROV G, et al.DBpedia-a crystallization point for the Web of data[J].Journal of Web Semantics, 2009, 7(3):154-165.
[6] SUCHANEK F M, KASNECI G, WEIKUM G.YAGO:a large ontology from Wikipedia and WordNet[J].Journal of Web Semantics, 2008, 6(3):203-217.
[7] REBELE T, SUCHANEK F, HOFFART J, et al.YAGO:a multilingual knowledge base from Wikipedia, WordNet, and GeoNames[C]//Proceedings of International Semantic Web Conference.Berlin, Germany:Springer, 2016:177-185.
[8] NAVIGLI R, PONZETTO S P.BabelNet:the automatic construction, evaluation and application of a wide-coverage multilingual semantic network[J].Artificial Intelligence, 2012, 193:217-250.
[9] BORDES A, USUNIER N, GARCIADURAN A, et al.Translating embeddings for modeling multi-relational data[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems.New York, USA:ACM Press, 2013:2787-2795.
[10] SCARSELLI F, GORI M, TSOI A C, et al.The graph neural network model[J].IEEE Transactions on Neural Networks, 2009, 20(1):61-80.
[11] WANG Z C, LÜ Q, LAN X H, et al.Cross-lingual knowledge graph alignment via graph convolutional networks[C]//Proceedings of 2018 Conference on Empirical Methods in Natural Language Processing.Stroudsburg, USA:Association for Computational Linguistics, 2018:349-357.
[12] KIPF T N, WELLING M.Semi-supervised classification with graph convolutional networks[EB/OL].[2020-12-07].https://arxiv.org/abs/1609.02907.
[13] SCHLICHTKRULL M S, KIPF T, BLOEM P, et al.Modeling relational data with graph convolutional networks[C]//Proceedings of European Semantic Web Conference.Berlin, Germany:Springer, 2018:593-607.
[14] WU Y T, LIU X, FENG Y S, et al.Jointly learning entity and relation representations for entity alignment[C]//Proceedings of 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing.Stroudsburg, USA:Association for Computational Linguistics, 2019:240-249.
[15] VELIČKOVIĆ P, CUCURULL G, CASANOVA A, et al.Graph attention networks[EB/OL].[2020-12-07].http://arxiv.org/pdf/1710.10903.
[16] NGOMO A N, AUER S.LIMES:a time-efficient approach for large-scale link discovery on the Web of data[C]//Proceedings of International Joint Conference on Artificial Intelligence.New York, USA:ACM Press, 2011:2312-2317.
[17] HAO Y C, ZHANG Y Z, HE S Z, et al.A joint embedding method for entity alignment of knowledge bases[M].Berlin, Germany:Springer, 2016:3-14.
[18] CHEN M H, TIAN Y T, YANG M H, et al.Multilingual knowledge graph embeddings for cross-lingual knowledge alignment[C]//Proceedings of International Joint Conference on Artificial Intelligence.Berlin, Germany:Springer, 2017:1511-1517.
[19] SUN Z Q, HU W, LI C K.Cross-lingual entity alignment via joint attribute-preserving embedding[C]//Proceedings of International Semantic Web Conference.Berlin, Germany:Springer, 2017:628-644.
[20] MIKOLOV T, CHEN K, CORRADO G, et al.Efficient estimation of word representations in vector space[EB/OL].[2020-12-07].http://arxiv.org/abs/1301.3781.
[21] SUN Z Q, HU W, ZHANG Q H, et al.Bootstrapping entity alignment with knowledge graph embedding[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence.Berlin, Germany:Springer, 2018:4396-4402.
[22] ZHANG Q H, SUN Z Q, HU W, et al.Multi-view knowledge graph embedding for entity alignment[EB/OL].[2020-12-07].http://arxiv.org/abs/1906.02390v1.
[23] SHI X F, XIAO Y H.Modeling multi-mapping relations for precise cross-lingual entity alignment[C]//Proceedings of 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing.Stroudsburg, USA:Association for Computational Linguistics, 2019:813-822.
[24] WU Y T, LIU X, FENG Y S, et al.Relation-aware entity alignment for heterogeneous knowledge graphs[EB/OL].[2020-12-07].https://arxiv.org/abs/1908.08210.
[25] SUN Z Q, WANG C M, HU W, et al.Knowledge graph alignment network with gated multi-hop neighborhood aggregation[C]//Proceedings of 2020 AAAI Conference on Artificial Intelligence.Palo Alto, USA:AAAI Press, 2020:222-229.
[26] YANG H W, ZOU Y Y, SHI P, et al.Aligning cross-lingual entities with multi-aspect information[C]//Proceedings of 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing.Stroudsburg, USA:Association for Computational Linguistics, 2019:4430-4440.
[27] SRIVASTAVA R K, GREFF K, SCHMIDHUBER J.Highway networks[EB/OL].[2020-12-07].https://zhuanlan.zhihu.com/p/38130339.
[28] RAHIMI A, COHN T, BALDWIN T.Semi-supervised user geolocation via graph convolutional networks[EB/OL].[2020-12-07].https://arxiv.org/abs/1804.08049.

选择文件类型/文献管理软件名称

选择包含的内容