• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

He, Meng (He, Meng.) | Duan, Lijuan (Duan, Lijuan.) | Zhang, Baochang (Zhang, Baochang.) | Han, Shengwen (Han, Shengwen.)

收录:

EI Scopus

摘要:

A knowledge graph is a knowledge base of graph structure that stores massive facts and their relations in the form of triplets. Embedding entities and relations in knowledge graph into low-dimensional continuous vector space is of great significance for downstream tasks, whereas most existing methods give an end-to-end fixed representation. Based on deep metric learning, we give different embeddings for the same entity in different relations and positions, thus dynamically representing entities in knowledge graph and effectively modeling complex relations. In addition, a path-based negative sampling method is proposed to widen the distance between similar entities to better deal with the aggregation problem of embedding entities in the representation space under one-to-many relation. Experiments show that the MRR and Hit@1 of this method on the linked prediction dataset FB15k-237 reach 0.360 and 0.267 respectively, which are higher than the mainstream distance models and semantic matching models. Finally, the MRR-Dimension curves demonstrates that our model can perform well in both low and high embedding dimensions and has the potential to be applied to large-scale knowledge graph. © 2023 Copyright held by the owner/author(s).

关键词:

Semantics Knowledge graph Graph embeddings Deep learning Vector spaces

作者机构:

  • [ 1 ] [He, Meng]Faculty of Information Technology, Beijing University of Technology, Beijing Key Laboratory of Trusted Computing, National Engineering Laboratory for Key Technologies of Information Security Level Protection, China
  • [ 2 ] [Duan, Lijuan]Faculty of Information Technology, Beijing University of Technology, Beijing Key Laboratory of Trusted Computing, National Engineering Laboratory for Key Technologies of Information Security Level Protection, China
  • [ 3 ] [Zhang, Baochang]Institute of Artificial Intelligence, Beihang University, China
  • [ 4 ] [Han, Shengwen]Faculty of Information Technology, Beijing University of Technology, China

通讯作者信息:

电子邮件地址:

查看成果更多字段

相关关键词:

相关文章:

来源 :

年份: 2023

页码: 381-387

语种: 英文

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 2

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 1

归属院系:

在线人数/总访问数:458/4954046
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司