Bridging Text Space and Knowledge Space via Transference Methods

Introducing the words of texts, entities, and relations of a knowledge graph (KG) into the same semantic space has great significance in KG complement and knowledge computing. Current methods mainly utilize the "alignment constraint"of words and entities to construct uniform objective functions. However, the "alignment constraint"limits the joint representation space to specific KGs and texts. Meanwhile, the representation effect still suffers from the scale of the "alignment constraint". This paper propose a novel transference framework, the method firstly learns the text representation space and KG representation space independently, and then transfers the word representation in the text space to the knowledge space with projection models, and finally constructs a joint representation space. Our approach can decrease the dependency on "alignment constraint", and allow two spaces to be optimized and extended independently. Hence, it has better flexibility, general applicability and helps improve the capability of the joint representation space. Further more, to enhance the word transference performance, we incorporate the relation constraint into the mapping models. To the best of our knowledge, this is the first study using transference method to construct the joint semantic space. The experimental results show that linear mapping models are more suitable than nonlinear models during the projection process. The results of word analogy and relation extraction tasks illustrate the effectiveness of our method compared with state-of-the-art methods.