计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 230200041-6.doi: 10.11896/jsjkx.230200041
迟棠, 车超
CHI Tang, CHE Chao
摘要： 实体对齐是知识融合中的关键步骤,用于解决多源知识图谱中实体冗余、指代不明等问题。目前,大多数的实体对齐方法主要依赖于邻域网络,而忽略了关系间的连通以及属性信息,导致模型无法捕捉到复杂关系,额外信息也没有被充分利用。针对上述问题,提出一种迭代式关系图匹配和属性语义嵌入的实体对齐方法,将〈头实体,关系,尾实体〉进行转置,生成〈头关系,实体,尾关系〉构建,与实体图相对应的关系图,接着利用注意力机制编码实体和关系表示,二者通过相互迭代,能够更好地表示实体,再融合属性表示最终判定两个实体是否对齐。实验结果表明,本模型在DBP15K 3个跨语言数据集中显著优于其他6种方法,相比于最好方法Hit@1指标提升了4％,证明了关系匹配和属性语义的有效性。
中图分类号:
| [1]RIVERA-TRIGUEROS I.Machine translation systems andquality assessment:a systematic review[J].Language Resources and Evaluation,2022,56(2):593-619. [2]KO H,LEE S,PARK Y,et al.A survey of recommendation systems:recommendation models,techniques,and application fields[J].Electronics,2022,11(1):141-188. [3]XIAO J,YAO A,LIU Z,et al.Video as conditional graph hierarchy for multi-granular question answering[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2022:2804-2812. [4]FORMICA A,TAGLINO F.Semantic relatedness in DBpedia:Acomparative and experimental assessment[J].Information Sciences,2023,621:474-505. [5]LIU J,CHABOT Y,TRONCY R,et al.From tabular data toknowledge graphs:A survey of semantic table interpretation tasks and methods[J].Journal of Web Semantics,2022,76(3):1-28. [6]NAVIGLI R,BEVILACQUA M,CONIA S,et al.Ten Years of BabelNet:A Survey[C]//Proceedings of the International Joint Conference on Artificial Intelligenc.Montreal,2021:4559-4567. [7]LEONE M,HUBER S,ARORA A,et al.A critical re-evaluation of neural methods for entity alignment[J].Proceedings of the VLDB Endowment,2022,15(8):1712-1725. [8]ZHU Y,LIU H,WU Z,et al.Relation-aware neighborhoodmatching model for entity alignment[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:4749-4756. [9]ZHU J,HUANG C,DE MEO P.DFMKE:A dual fusion multi-modal knowledge graph embedding framework for entity alignment[J].Information Fusion,2023,90:111-119. [10]ZENG K,DONG Z,HOU L,et al.Interactive ContrastiveLearning for Self-Supervised Entity Alignment[C]//Proceedings of the 31st ACM International Conference on Information &Knowledge Management.Atlanta,USA,2022:2465-2475. [11]ZHU B,BAO T,HAN J,et al.Cross-lingual knowledge graph entity alignment by aggregating extensive structures and specific semantics[J].Journal of Ambient Intelligence and Humanized Computing,2023(14):12609-12616. [12]XIN K,SUN Z,HUA W,et al.Large-scale Entity Alignment via Knowledge Graph Merging,Partitioning and Embedding[C]//Proceedings of the 31st ACM International Conference on Information & Knowledge Management.Atlanta GA,USA,2022:2240-2249. [13]NGOMO A-C N,AUER S.LIMES－a time-efficient approach for large-scale link discovery on the web of data[C]//Twenty-Second International Joint Conference on Artificial Intelligence.Barcelona,Catalonia,Spain,2011. [14]JIMÉNEZ-RUIZ E,CUENCA GRAU B.Logmap:Logic-based and scalable ontology matching[C]//Proceedings of the 10th International Semantic Web Conference.Bonn,Germany,2011:273-288. [15]SUN Z,HUANG J,HU W,et al.Transedge:Translating relation-contextualized embeddings for knowledge graphs[C]//Proceedings of the18th International Semantic Web Conference.Auckland,New Zealand,2019:612-629. [16]YAN Z,PENG R,WANG Y,et al.CTEA:Context and topic enhanced entity alignment for knowledge graphs[J].Neurocomputing,2020,410:419-431. [17]SUN Z,HU W,ZHANG Q,et al.Bootstrapping entity alignment with knowledge graph embedding[C]//Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence.Macao,China,2019:5429-5435. [18]GAO Y,LIU X,WU J,et al.ClusterEA:scalable entity alignment with stochastic training and normalized mini-batch similari-ties[C]//Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.Washington DC,USA,2022:421-431. [19]WANG Z,YANG J,YE X.Knowledge graph alignment with entity-pair embedding[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing(EMNLP).2020:1672-1680. [20]CHEN M,SHI W,ZHOU B,et al.Cross-lingual Entity Alignment with Incidental Supervision[C]//Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics:Main Volume.2021:645-658. [21]ZHANG Z,ZHANG Z,ZHOU Y,et al.Adversarial attack against cross-lingual knowledge graph alignment[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.Online and Punta Cana,Dominican Republic,2021:5320-5337. [22]GUO L,HAN Y,ZHANG Q,et al.Deep reinforcement learning for entity alignment[C]//Proceedings of the60th Annual Meeting of the Association for Computational Linguistics.Dublin,2022:2754-2765. [23]YANG H W,ZOU Y,SHI P,et al.Aligning Cross-Lingual Entities with Multi-Aspect Information[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP).Hong Kong,China,2019:4431-4441. [24]WU Y,LIU X,FENG Y,et al.Jointly Learning Entity and Relation Representations for Entity Alignment[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP).Hong Kong,China,2019:240-249. [25]WANG Z,LV Q,LAN X,et al.Cross-lingual knowledge graph alignment via graph convolutional networks[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.Brussels,Belgium,2018:349-357. [26]WU Y,LIU X,FENG Y,et al.Neighborhood Matching Net-work for Entity Alignment[C]//Proceedings of the 58th AnnualMeeting of the Association for Computational Linguistics.2020:6477-6487. [27]GAO J,LIU X,CHEN Y,et al.MHGCN:Multiview highway graph convolutional network for cross-lingual entity alignment[J].Tsinghua Science and Technology,2021,27(4):719-728. [28]MAO X,WANG W,WU Y,et al.Boosting the speed of entity alignment 10×:Dual attention matching network with norma-lized hard sample mining[C]//Proceedings of the Web Confe-rence 2021.Ljubljana,Slovenia,2021:821-832. [29]WU J,LI B,QIN Y,et al.A multiscale graph convolutional network for change detection in homogeneous and heterogeneous remote sensing images[J].International Journal of Applied Earth Observation and Geoinformation,2021,105(1):102615. |
|
||
首页