Text-enhanced representation learning for knowledge graph

Learning the representations of a knowledge graph has attracted significant research interest in the field of intelligent Web. By regarding each relation as one translation from head entity to tail entity, translation-based methods including TransE, TransH and TransR are simple, effective and achieving the state-of-the-art performance. However, they still suffer the following issues: (i) low performance when modeling 1-to-N, N-to-1 and N-to-N relations. (ii) limited performance due to the structure sparseness of the knowledge graph. In this paper, we propose a novel knowledge graph representation learning method by taking advantage of the rich context information in a text corpus. The rich textual context information is incorporated to expand the semantic structure of the knowledge graph and each relation is enabled to own different representations for different head and tail entities to better handle 1-to-N, N-to-1 and N-to-N relations. Experiments on multiple benchmark datasets show that our proposed method successfully addresses the above issues and significantly outperforms the state-of-the-art methods.