Entity Alignment for Cross-lingual Knowledge Graphwith Graph Convolutional Networks
Abstract
Graph convolutional network (GCN) is a promising approach that has recently been used to resolve
knowledge graph alignment. In this paper, we propose a new method to entity alignment for crosslingual knowledge graph. In the method, we design
a scheme of attribute embedding for GCN training.
Furthermore, GCN model utilizes the attribute embedding and structure embedding to abstract graph
features simultaneously. Our preliminary experiments show that the proposed method outperforms
the state-of-the-art GCN-based method