基于实体相似性的知识表示学习方法.

Knowledge representation learning aims to represent the entities and relationships in the knowledge graph as low-dimen sional dense real-valued vectors, which can effectively alleviate the data sparsity of the knowledge graph and significantly improve the calc ulation efficiency. However, most existing knowledge representation learning methods only treat entities as an integral part of triples, and do not consider the characteristics of entities themselves, such as entity simila rity . In order to strengthen the sema ntic expression of embedded vectors, this pap er proposed a representation learning method SimE based on entity similarity. The method first used the structural domain of the entity to measure the similarity of the entity, and then comb ined the simila rity of the entity and the Laplace feature map as a constraint of the representation learning method based on the fact of triples to form a j oint represe ntation. Experime ntal results show that the method is close to the best method c urrently in tasks such as link prediction and triple classification. [ABSTRACT FROM AUTHOR]