一种改进的基于TransE知识图谱表示方法  

An Improved TransE-Based Method for Knowledge Graph Representation

作　　者：陈文杰 文奕[1] 张鑫 杨宁[1] 赵爽 CHEN Wenjie;WEN Yi;ZHANG Xin;YANG Ning;ZHAO Shuang(Chengdu Library and Information Center,Chinese Academy of Sciences,Chengdu 610041,China)

机构地区：[1]中国科学院成都文献情报中心,成都610041

出　　处：《计算机工程》2020年第5期63-69,77,共8页Computer Engineering

基　　金：中国科学院“十三五”信息化项目(XXH13506)。

摘　　要：传统基于翻译模型的知识图谱表示方法难以处理一对多、多对一和多对多等复杂关系,而且通常独立地学习三元组而忽略了知识图谱的网络结构和语义信息。为解决该问题,构建一种基于TransE的TransGraph模型,该模型同时学习三元组和知识图谱网络结构特征,以有效增强知识图谱的表示效果。在此基础上,提出一种向量共享的交叉训练机制,从而实现网络结构信息和三元组信息的深度融合。在公开数据集上的实验结果表明,相比TransE模型,TransGraph模型在链路预测和三元组分类2个任务中的HITS@10、准确率指标均得到显著提升。It is difficult for traditional representation methods based on translation models for knowledge graph to deal with complex relationships such as one to many,many to one and many to many relations.Also,they usually neglect the network structure and semantic information of knowledge graph when studying triples.To solve these problems,this paper proposes a TransGraph model based on TransE.The model learns triples and the network structure features of knowledge graph at the same time,so as to enhance the representation performance of knowledge graph.On this basis,a cross training mechanism of vector sharing is proposed in order to realize the deep fusion of network structure information and triple information.Experimental results on open datasets show that the HITS@10 and accuracy of TransGraph are significantly improved in link prediction and triple classification compared with the TransE model.

关 键 词：知识图谱 表示学习 TransE模型 链路预测 神经网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]