OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1117–1128 August 1–6, 2021. ©2021 Association for Computational Linguistics 1117 OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding Yuejia Xiang1,2∗,ZihengZhang1∗,JiaoyanChen3,XiChen1,2†,ZhenxiLin1,YefengZheng1 1Tencent Jarvis Lab, Shenzhen, China 2Platform and Content Group, Tencent, Shenzhen, China 3Department of Computer Science, University of Oxford, UK {yuejiaxiang,zihengzhang}@tencent.com, jiaoyan.chen@cs.ox.ac.uk {jasonxchen,chalerislin,yefengzheng}@tencent.com Abstract Semantic embedding has been widely investi- gated for aligning knowledge graph (KG) en- tities. Current methods have explored and uti- lized the graph structure, the entity names, and attributes, but ignore the ontology (or ontologi- cal schema) which contains critical meta infor- mation such as classes and their membership relationships with entities. In this paper, we propose an ontology-guided entity alignment method named OntoEA, where both KGs and their ontologies are jointly embedded, and the class hierarchy and the class disjointness are utilized to avoid false mappings. Extensive experiments on seven public and industrial benchmarks have demonstrated the state-of- the-art performance of OntoEA and the effec- tiveness of the ontologies. 1 Introduction Knowledge graphs (KGs) that are composed of entities and facts in the RDF form (i.e., RDF triples) are of vital importance in various applications, such as search engines and personal assistants (Hogan et al., 2020). Although there have been several large-scale KGs, the content of one individual KG is often incomplete, especially in supporting some domain-specific applications such as clinical AI assistants. As these KGs are developed separately, they are usually heterogeneous and supplementary to each other. Thus it becomes urgently needed to align multiple KGs (i.e., matching the equivalent elements) to fully explore their usability. Recently, a few embedding-based methods have been proposed for entity alignment (EA) (Sun et al., 2020b; Zhang et al., 2020; Qi et al., 2021), in which entities are embedded into vectors and the equiv- alent entities are determined via calculating the similarity of their vectors. They extend the em- bedding of one KG to the embedding of multiple *Equal contribution †Corresponding author Queen Victoria VICTORIA Victoria Royalty ORG Agent Politician Person Ontologies KG1 KG2 e1 e2 e3 Edward VII predecessor John Brown employer Frogmore Estate sépulture Édouard VII successeur Lovan Ho rector Hong Kong locationCity membership subClassOf wrong entity mapping Educational Organization Organization University class mapping right entity mapping Figure 1: A class conflict example in entity alignment. KGs into one vector space by, for instance, a trans- formation matrix, which is learnt from annotated mappings (a.k.a. seed mappings). They also utilize the entity names and attributes besides the graph structures for better performance. These methods, however, all ignore the ontology (or ontological schema) which is an important part of many KGs such as DBpedia (Auer et al., 2008) and Wikidata (Vrandeˇci´c and Kr¨otzsch, 2014) as meta informa- tion for higher quality and usability. The ontology typically contains hierarchical classes and proper- ties, and optionally defines some logical constraints such as the class disjointness, the property domain and range (Horrocks, 2008). Meanwhile, the KG usually clarifies the membership relationship be- tween entities and classes. The entity mappings …

Content truncated to 500 words