基于贝叶斯规则的具有层次注意力的知识补全  

Bayesian Rule-based Knowledge Completion with Hierarchical Attention

作　　者：单晓欢 赵雪 陈廷伟[1] SHAN Xiaohuan;ZHAO Xue;CHEN Tingwei(College of Information,Liaoning University,Shenyang 110036,China)

机构地区：[1]辽宁大学信息学院,沈阳110036

出　　处：《计算机科学》2023年第11期234-240,共7页Computer Science

基　　金：国家重点研发计划。

摘　　要：知识图谱作为大数据时代的人工智能,被广泛应用于诸多领域,然而知识图谱普遍存在不完备性及稀疏性等问题。知识补全作为知识获取的子任务,旨在通过知识库中已知三元组来预测缺失的链接。然而现有方法普遍忽略了实体类型信息联合邻域信息对提高知识补全准确性的辅助作用,同时还存在特征信息被紧密编码到目标函数,导致集成操作高度依赖训练过程等问题。为此,提出了一种基于贝叶斯规则的具有层次注意力的知识补全方法。首先将实体类型和邻域信息视为层次结构,按关系进行分组,并独立计算组内各类信息的注意力权重。然后将实体类型和邻域信息编码为先验概率,将实例信息编码为似然概率,且按照贝叶斯规则将二者进行组合。实验结果表明,所提方法在FB15k数据集上的MRR(Mean Reciprocal Rank)指标比ConvE提高14.4%,比TKRL提高10.7%;在FB15k-237数据集上的MRR指标比TACT提高了2.1%。在FB15k,FB15k-237和YAGO26K-906数据集上,其Hits@1达到了77.5%,73.8%和95.1%,证明了引入具有层次结构的类型信息和邻域信息能够为实体嵌入更丰富、准确的描述信息,进而提升知识补全的精度。As artificial intelligence in the big data era,knowledge graphs are widely used in many fields.Knowledge graphs gene-rally suffer from incompleteness and sparsity.As a sub-task of knowledge acquisition,knowledge completion aims to predict mis-sing links from known triples in the knowledge base.However,existing knowledge completion methods generally ignore the auxi-liary role of entity type jointly with neighborhood information,which can improve the knowledge completion accuracy.There are other problems such as feature information closely encodes into the objective function,and integration operations depend on the training process highly.To this end,a Bayesian rule-based knowledge completion method with hierarchical attention is proposed.Firstly,it regards entity type and neighborhood information as hierarchical structures,groups by relationship.It calculates each type information’s attention weights independently.Then the entity types and neighborhood information encoding are regarded as the prior probability.The instance information encoding as likelihood probability.The two are combined according to the Bayesian rule.Experimental results show that the mean reciprocal rank(MRR)metric in the FB15k dataset improves 14.4%over ConvE and 10.7%over TKRL.The MRR metric in the FB15k-237 dataset improves 2.1%over TACT.In the FB15k,FB15k-237 and YAGO26K-906 datasets,its Hits@1 reaches 77.5%,73.8%and 95.1%respectively,which demonstrates the introduction of type information and neighborhood information with hierarchical structure can embed richer and more accurate descriptive information for entities,and thus improve the accuracy of knowledge completion.

关 键 词：贝叶斯规则 实体类型 多层注意力 知识图谱补全 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]