AAAI Publications, Twenty-Eighth AAAI Conference on Artificial Intelligence

Font Size: 
Content-Structural Relation Inference in Knowledge Base
Zeya Zhao, Yantao Jia, Yuanzhuo Wang

Last modified: 2014-06-21

Abstract


Relation inference between concepts in knowledge base has been extensively studied in recent years. Previous methods mostly apply the relations in the knowledge base, without fully utilizing the contents, i.e., the attributes of concepts in knowledge base. In this paper, we propose a content-structural relation inference method (CSRI) which integrates the content and structural information between concepts for relation inference. Experiments on data sets show that CSRI obtains 15% improvement compared with the state-of-the-art methods.

Keywords


relation inference, Knowledge Bases, attributes, relation path

Full Text: PDF