Neighborhood Mixture Model for Knowledge Base Completion

摘要: Knowledge bases are useful resources for many natural language processing tasks, however, they far from complete. In this paper, we define a novel entity representation as mixture of its neighborhood in the knowledge base and apply technique on TransE-a well-known embedding model completion. Experimental results show that information significantly helps to improve TransE model, leading better performance than obtained by other state-of-the-art models three benchmark datasets triple classification, prediction relation tasks.