Knowledge Graph Embedding Based On Multi-information Fusion

Abstract

The knowledge graph embedding aims to represent the elements in the knowledge graph as low-dimensional dense distributed representation vectors in the continuous semantic space, which has achieved good results in the knowledge graph completion. However, the existing embedding methods do not make full use of and extract the existing information in the knowledge graph, which will directly affect the quality of knowledge graph embedding. In order to make the embedded model can fuse more reasonable c0onstraints and rich semantic information, in this paper, the entities in the traditional triples are divided into concepts and entities, and through the conceptual constraint information generated by the entity, the structural information of the triple and the entity description text information encoded by the deep learning, the hidden relationship between the existing entities in the knowledge graph is mined, and a more accurate semantic space representation is obtained. Experiments show that the embedded model proposed in this paper has better performance.