Learning entity and relation embeddings for knowledge graph completion

Knowledge graph completion aims to perform link pre-diction between entities. In this paper, we consider the approach of knowledge graph embeddings. Recently, models such as TransE and TransH build entity and re-lation embeddings by regarding a relation as translation from head entity to tail entity. We note that these model-s simply put both entities and relations within the same semantic space. In fact, an entity may have multiple as-pects and various relations may focus on different as-pects of entities, which makes a common space insuf-ficient for modeling. In this paper, we propose Tran-sR to build entity and relation embeddings in separate entity space and relation spaces. Afterwards, we learn embeddings by first projecting entities from entity s-pace to corresponding relation space and then building translations between projected entities. In experiments, we evaluate our models on three tasks including link prediction, triple classification and relational fact ex-traction. Experimental results show significant and con-sistent improvements compared to state-of-the-art base-lines including TransE and TransH. The source code of this paper can be obtained fro