融合HousE和注意力机制的知识推理模型  

Knowledge Reasoning Model Combining HousE with Attention Mechanism

作　　者：朱玉亮 刘俊涛[1] 饶子昀 张毅 曹万华[1] ZHU Yuliang;LIU Juntao;RAO Ziyun;ZHANG Yi;CAO Wanhua(Wuhan Digital Engineering Institute,Wuhan 430205,China)

机构地区：[1]武汉数字工程研究所,武汉430205

出　　处：《计算机科学》2024年第S01期135-142,共8页Computer Science

基　　金：十四五装备预先研究项目(50902010503)。

摘　　要：知识推理技术是解决知识图谱缺失问题所提出的方法,并在近年来不断发展。为了解决推理中准确度低、可解释性差、适用性不强等问题,提出了一种融合注意力机制和HousE的知识推理模型Att-HousE。该模型由一个带注意力机制的规则生成器和一个带HousE嵌入的规则预测器组成,规则生成器生成推理需要的规则并传入预测器,预测器更新并得到不同规则的得分,然后通过EM算法不断训练优化生成器与预测器。具体而言,该模型是建立在RNNLogic的基础上并作出改进,注意力机制可以选取更值得关注的关系作为规则,提高了模型准确度,HousE嵌入则在处理复杂关系上更具有灵活性,并适用于建立多边关系。在公开实验数据集上的结果表明,Att-HousE在FB15K-237上做推理任务时,MRR指标整体比RNNLogic高出6.3%;在稀疏数据集WN18RR上,Hits@10指标整体比RNNLogic高出2.7%,证明了引入HousE和注意力机制后可以更全面地抓取和形成多边关系,提升知识推理的精度。Knowledge reasoning technology is a method proposed to solve the problem of missing knowledge graphs and has been continuously developed in recent years.In order to solve the problems of low accuracy,poor interpretability,and weak applicability in knowledge reasoning,a knowledge reasoning model called Att-HousE,which combines HousE with Attention Mechanism,is proposed.It consists of a rule generator with attention mechanism and a rule predictor with HousE.The rule generator generates the rules required for reasoning and passes them into the predictor,which updates and then obtains scores for different rules.After that,the generator and predictor are continuously trained and optimized by the EM algorithm.Specifically,the model is based on RNNLogic and has been improved.The attention mechanism can select more noteworthy relationships as rules,improving the accuracy of the model.HousE has more flexibility in handling complex relationships and is suitable for establishing multilateral relationships.According to experimental results on public datasets,it indicates that Att-HousE’s MRR is 6.3%higher than that of RNNLogic when doing reasoning tasks on FB15K-237.For the sparse dataset WN18RR,the Hits@10 of Att-HousE is 2.7%higher than that of RNNLogic.It is demonstrated that the introduction of HousE and attention mechanism can more comprehensively grasp and form multilateral relationships,which can improve the accuracy of knowledge reasoning.

关 键 词：知识图谱补全 知识推理 注意力机制 知识表示 EM算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]