Cross-Knowledge Graph Relation Completion for Non-isomorphic Cross‐lingual Entity Alignment

Abstract

The Cross-Lingual Entity Alignment (CLEA) aims to find the aligned entities that refer to the same identity from two Knowledge Graphs (KGs) in different languages.In real-world applications, the neighborhood structures of the same entities in different KGs tend to be non-isomorphic, which makes the entity representation contain diverse semantics information and poses a great challenge for CLEA.In this paper, we address this challenge from two perspectives.On the one hand, cross-KG relation completion rules are designed with the alignment constraint of entities and relations to improve the isomorphism of two KGs.On the other hand, a representation method combining isomorphic weights is designed to include more isomorphic semantics for counterpart entities, which will benefit CLEA.Experimental results show that our model can improve the isomorphism of two KGs and the alignment performance, especially for two non-isomorphic KGs.