NGDcrm:a numeric graph dependency-based conflict resolution method for knowledge graph

作     者：Ma Jiangtao Wang Yanjun Chen Xueting Qiao Yaqiong 马江涛;Wang Yanjun;Chen Xueting;Qiao Yaqiong

作者机构：College of Computer and Communication EngineeringZhengzhou Universily of Lighl IndustryZhengzhou 450002P.R.China State Key Laboratory of Mathematical Engineering and Advanced ComputingZhengzhou 450002P.R.China School of Computer&Communication EngineeringUniversity of Science and Technology BeijingBeijing 100083P.R.China School of Information EngineeringNorth China University of W ater Resources and Electric PowerZhengzhou 450046P.R.China 

出 版 物：《High Technology Letters》 (高技术通讯（英文版）)

年 卷 期：2021年第27卷第2期

页      面：153-162页

核心收录：

学科分类：07[理学] 070104[理学-应用数学] 0701[理学-数学] 

基　　金：Supported by the Henan Province Science and Technology Department Foundation(No.202102310237,192102210133,202102310295) the Doctoral Research Fund of Zhengzhou University of Light Industry(No.2018BSJJ039) the Internet Medical and Health Service Henan Collaborative Innovation Center Open Project Fund(No.IH2019006) 

主　　题：dependency graph knowledge conflict resolution knowledge graph(KG) numeric graph dependency(NGD) 

摘      要：Knowledge graph(KG)conflict resolution is to solve knowledge conflicts problem in the construction of *** at the problem of KG conflict resolution,a KG conflict resolution algorithm NGDcrm is proposed,which is a numeric graph dependency-based conflict resolution *** utilizes the dependency graph to perform arithmetic calculation and predicate comparison of numerical entity knowledge in the *** first uses a parallel segmentation method to segment the KG;then,it extracts the features of the KG according to KG embedding;finally,it uses numerical graph dependencies to detect and correct the wrong facts in the KG based on the extracted *** experimental results on real data show that NGDcrm is better than the state-of-the-art knowledge conflict resolution *** them,the AUC value of NGDcrm on the DBpedia dataset is 15.4%higher than the state-of-the-art method.