Joint entity-relation knowledge embedding via cost-sensitive learning

作     者：Sheng-kang YU Xue-yi ZHAO Xi LI Zhong-fei ZHANG 

作者机构：College of Information Science and Electronic Engineering Zhejiang University Hangzhou 310027 China College of Computer Science and Technology Zhejiang University Hangzhou 310027 China 

基　　金：Project supported by the National Basic Research Program (973) of China (No. 2015CB352302) and the National Natural Science Foundation of China (Nos. U1509206 and 61472353) 

出 版 物：《Frontiers of Information Technology & Electronic Engineering》 (信息与电子工程前沿（英文版）)

年 卷 期：2017年第18卷第11期

页      码：1867-1873页

摘      要：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.

主 题 词：Knowledge embedding Joint embedding Cost-sensitive learning 

学科分类：12[管理学] 1201[管理学-管理科学与工程类] 08[工学] 081201[081201] 0812[工学-测绘类] 

核心收录：

D　O　I：10.1631/FITEE.1601255

馆 藏 号：203281830...