融合HousE和注意力机制的知识推理模型
Knowledge Reasoning Model Combining HousE with Attention Mechanism
朱玉亮 1刘俊涛 1饶子昀 1张毅 1曹万华1
作者信息
- 1. 武汉数字工程研究所 武汉 430205
- 折叠
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.
Abstract
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 applicabili-ty 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.Af-ter 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 comprehen-sively 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Key words
Knowledge graph completion/Knowledge reasoning/Attention mechanism/Knowledge representation/EM algorithm引用本文复制引用
基金项目
装备预研项目(十四五)(50902010503)
出版年
2024
NETL
NSTL
万方数据