Frontiers of Information Technology & Electronic Engineering
>> 2017,
Volume 18,
Issue 11
doi:
10.1631/FITEE.1601255
Article
Joint entity–relation knowledge embedding via cost-sensitive learning
. College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China.. College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China.
Available online: 2018-03-08
Next
Previous
Abstract
As a joint-optimization problem which simultaneously fulfills two different but correlated embedding tasks (i.e., entity embedding and relation embedding), knowledge embedding problem is solved in a joint embedding scheme. In this embedding scheme, we design a joint compatibility scoring function to quantitatively evaluate the relational facts with respect to entities and relations, and further incorporate the scoring function into the maxmargin structure learning process that explicitly learns the embedding vectors of entities and relations using the context information of the knowledge base. By optimizing the joint problem, our design is capable of effectively capturing the intrinsic topological structures in the learned embedding spaces. Experimental results demonstrate the effectiveness of our embedding scheme in characterizing the semantic correlations among different relation units, and in relation prediction for knowledge inference.