FuAlign: Cross-lingual entity alignment via multi-view representation learning of fused knowledge graphs

Chenxu Wang, Zhenhao Huang, Yue Wan, Junyu Wei, Junzhou Zhao, Pinghui Wang

Abstract: Highlights•We propose a novel entity alignment framework by fusing knowledge graphs first.•We develop a multi-view embedding model to encode different information into a unified embedding space.•We develop a reliability-based stable matching algorithm to address the low reliability matching problem.•We conduct extensive experiments to evaluate the effectiveness of the method.