摘要
针对现有时序知识图谱推理中外推方法没有充分利用时间信息的问题,受张量分解模型的启发,提出将关系嵌入分为静态和动态(时序)2个部分,并通过头实体嵌入、关系嵌入和所有实体嵌入之间的双线性评分函数,计算得到对象实体的概率,从而预测对象实体。最后,在3个数据集上的实验结果验证了该方法的有效性。
In response to the insufficient utilization of temporal information in existing extrapolation methods for reasoning of temporal knowledge graphs,inspired by the tensor decomposition model,the relational embedding was divided into static and dynamic(temporal)parts.The probability of the object entity was then calculated through the bilinear scoring function between head entity embedding,relational embedding,and all entity embedding.Finally,the experimental results on three datasets verified the effectiveness of this method.
作者
刘伟
谢璐钧
张智慧
陈亚繁
LIU Wei;XIE Lujun;ZHANG Zhihui;CHEN Yafan(School of Automation,Beijing Information Science&Technology University,Beijing 100192,China;Beijing Aerospace Smart Manufacturing Technology Development Co.,Ltd.,Beijing 100143,China)
出处
《北京信息科技大学学报(自然科学版)》
2024年第1期49-54,共6页
Journal of Beijing Information Science and Technology University
基金
国家重点研发计划(2019YFB2103103)
北京信息科技大学校科研基金项目(2022XJJ11)。
关键词
时序知识图谱
表示学习
张量分解
temporal knowledge graph
representation learning
tensor decomposition