摘要
知识图谱是真实世界三元组的结构化表示,通常三元组被表示成头实体、关系、尾实体的形式。针对知识图谱中广泛存在的数据稀疏问题,提出了一种将四元数作为关系旋转的知识图谱补全方法。文中使用极具表现力的超复数表示对实体和关系进行建模,以进行链接预测。这种超复数嵌入用于表示实体,关系则被建模为四元数空间中的旋转。具体来说,将每个关系定义为超复数空间中头实体到尾实体的旋转,用于推理和建模各种关系模式,包括对称/反对称、反转和组合。在公开的数据集WN18RR和FB15K-237上进行相关的链接预测实验,实验结果表明,在WN18RR数据集中,其平均倒数排名(Mean Reciprocal Rank,MRR)比RotatE的提高了4.6%,其Hit@10比RotatE的提高了1.7%;在FB15K-237数据集中,其平均倒数排名比RotatE的提高了5.6%,其Hit@3比RotatE的提高了1.4%。该实验证明,使用四元数作为关系旋转的知识图谱补全方法可以有效提高三元组预测精度。
Knowledge graph is a structured representation of real-world triples.Typically,triples are represented in the form of head entity,relationship entity and tail entity.Aiming at the data sparse problem widely existing in knowledge graph,this paper proposes a knowledge graph completion method using quaternions as relational rotation.In this paper,we model entities and relations in the expressive hyper-complex representations for link prediction.This hyper-complex embedding is used to represent entities,and relations are modelled as rotations in quaternion space.Specifically,we define each relation as a rotation from the head entity to the tail entity in the hyper-complex space,which could be used to infer and model diverse relation patterns,including symmetry/anti-symmetry,reversal and combination.In the experiment,the public datasets WN18RR and FB15K-237 are used for the related link prediction experiment.Experimental results show that on the WN18RR dataset,its mean reciprocal rank(MRR)is 4.6%higher than RotatE,and its Hit@10 is 1.7%higher than RotatE.On the FB15K-237 dataset,its MRR is 5.6%higher than RotatE,its Hit@3 is 1.4%higher than RotatE.Experiments show that the knowledge graph completion method using quaternions as relational rotation can effectively improve the prediction accuracy of triples.
作者
陈恒
王维美
李冠宇
史一民
CHEN Heng;WANG Wei-mei;LI Guan-yu;SHI Yi-ming(Faculty of Information Science&Technology,Dalian Maritime University,Dalian,Liaoning 116026,China;Research Center for Language Intelligence,Dalian University of Foreign Languages,Dalian,Liaoning 116044,China)
出处
《计算机科学》
CSCD
北大核心
2021年第5期225-231,共7页
Computer Science
基金
国家自然科学基金项目(61976032,61806038,61602076,61702072)
辽宁省高等学校基本科研项目(2017JYT09)
大连外国语大学科研创新团队(2016CXTD06)。
关键词
知识图谱
四元数
知识图谱补全
超复数表示
链接预测
Knowledge graph
Quaternion
Knowledge graph completion
Hyper-complex representation
Link prediction
