EASA: Entity Alignment Algorithm Based on Semantic Aggregation and Attribute Attention

Abstract

Numerous knowledge bases have been published on the web, and there are serious heterogeneous problems among them. Unifying these knowledge bases at the semantic level can better promote the development of the Linked Data Project. Various effective methods, the mainstream one of which is the iterative entity alignment algorithm based on TransE (Translation-based Embedding, an efficient knowledge graph embedding representation algorithm), have been put forward to solve the heterogeneous problems among knowledge bases. Although the TransE-based iterative entity alignment algorithm can shorten the distance between two entities with the same semantics, it has low accuracy because it ignores the importance of semantic aggregation generated by many attributes of entities in the entity alignment process. To solve this problem, a novel entity alignment algorithm based on semantic aggregation and attribute attention, named EASA, is proposed in this paper. On the one hand, semantic aggregation of entities can be generated by different attributes and attribute values. On the other hand, the addition of attribute attention can be used to distinguish the different roles of different attributes in the entity alignment process. The experimental results show that our method achieves significant improvements compared to baselines for entity alignment on Chinese and English datasets. The data and source code for this paper can be obtained from https://www.github.com/xinan711456/EASA.

Keywords

• Entity alignment
• semantic aggregation
• attribute attention
• knowledge base embedding