摘要
针对当前OWL知识表示学习方法存在的概念层和实例层复杂语义信息联合表征能力不足等问题,提出一种概念-属性-实例多语义视图驱动的OWL图谱知识表示学习方法(MSV-KRL).该方法采用“多语义视图划分、语义感知自监督进阶训练、多任务联合表示学习”的3阶段架构.首先,MSV-KRL在OWL2Vec*的基础上,优化OWL到RDF图结构的映射策略,提出5类细粒度语义视图划分策略.其次,通过语义视图内随机游走和标注属性替换策略,生成序列化进阶训练数据,并开展预训练模型的自监督进阶训练,以提升其面向多语义视图上下文的适配能力.最后,在多任务学习框架下,通过多语义视图预测任务联合优化损失,实现对OWL知识图谱中概念、属性和实例复杂语义有效表示学习.实验结果表明,MSV-KRL在多个基准数据集上的表现优于现有先进的知识表示学习方法,且能适配于多种语言模型,有效提升OWL复杂语义的知识表示能力.
To address the issues in current OWL representation learning methods,which lack the ability to jointly represent complex semantic information across both the concept layer and the instance layer,an OWL representation learning approach using multi-semantic views of concepts,properties,and instances is proposed.The proposed method adopts a three-stage architecture including multi-semantic views partitioning,semantic-aware self-supervised post-training,and joint multi-task representation learning.First,MSV-KRL optimizes the mapping strategy from OWL to RDF graphs based on OWL2Vec*,and five fine-grained semantic view partitioning strategies are proposed.Subsequently,serialized post-training data is generated through the random walk and annotated attribute replacement strategy.The self-supervised post-training of the pre-trained model is then carried out to enhance adaptability to multi-semantic views.Finally,by employing a multi-task learning strategy,the complex semantic representation learning of concepts,properties,and instances in OWL graphs is achieved through joint optimization loss of multi-semantic view prediction tasks.Experimental results demonstrate that MSVKRL outperforms baseline representation learning methods on multiple benchmarks.MSV-KRL can be adapted to multiple language models,significantly improving the knowledge representation capability of OWL’s complex semantics.
作者
杨建喜
谢江村
李韧
杨小霞
肖桥
蒋仕新
贺丽荣
YANG Jian-Xi;XIE Jiang-Cun;LI Ren;YANG Xiao-Xia;XIAO Qiao;JIANG Shi-Xin;HE Li-Rong(School of Information Science and Engineering,Chongqing Jiaotong University,Chongqing 400074,China;College of Traffic and Transportation,Chongqing Jiaotong University,Chongqing 400074,China)
出处
《软件学报》
北大核心
2025年第12期5644-5673,共30页
Journal of Software
基金
国家自然科学基金(62003063)
重庆市教委科学技术研究重大项目(KJZD-M202300703)
重庆市教委科学技术研究青年项目(KJQN202200720)
重庆市自然科学基金面上项目(CSTB2023NSCQ-MSX0145)。
关键词
知识表示学习
OWL知识图谱
多语义视图
进阶训练
多任务学习
knowledge representation learning(KRL)
OWL knowledge graph
multi-semantic view
post-training
multi-task learning
