Multilingual knowledge graph completion based on structural features

Abstract Multilingual knowledge graph completion predicts missing facts in the target language knowledge graph by learning and inferring knowledge and rules in other language knowledge graphs. Existing methods tend to use aligned entities between knowledge graphs in different languages as alignment seeds, and receive information from them through alignment seeds to promote entity alignment between different knowledge graphs. However, these methods only consider the local structural information of the knowledge graph by aggregating entity neighborhood information through aligned entities, and ignore the global structural information. At the same time, the methods aboved are hardly to learn the entity representation with sparse neighborhood in isolated subgraphs. To address these two problems, this paper proposes a multilingual knowledge graph completion method based on double-branch graph neural network and self-supervised entity alignment (DBGNN-SSL). The global and local topological structures of the knowledge graph are learned through a double-branch graph attention neural network, and more aligned entities can be iteratively generated through self-supervised learning. The experimental results on datasets DBP-5L and E-PKG verify the effectiveness of the proposed method.