• 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:

Zhou, Yunfeng (Zhou, Yunfeng.) | Zhu, Cui (Zhu, Cui.) | Zhu, Wenjun (Zhu, Wenjun.) | Li, Hongyang (Li, Hongyang.)

收录:

EI Scopus SCIE

摘要:

Entity alignment refers to discovering the entity pairs with the same realistic meaning in different knowledge graphs. This technology is of great significance for completing and fusing knowledge graphs. Recently, methods based on knowledge representation learning have achieved remarkable achievements in entity alignment. However, most existing approaches do not mine hidden information in the knowledge graph as much as possible. This paper suggests SCMEA, a novel cross -lingual entity alignment framework based on multiaspect information fusion and bidirectional contrastive learning. SCMEA initially adopts diverse representation learning models to embed multi -aspect information of entities and integrates them into a unified embedding space with an adaptive weighted mechanism to overcome the missing information and the problem of differentaspect information are not uniform. Then, we propose a stacked relation -entity co -enhanced model to further improve the representations of entities, wherein relation representation is modeled using an Entity Collector with Global Entity Attention. Finally, a combined loss function based on improved bidirectional contrastive learning is introduced to optimize model parameters and entity representation, effectively mitigating the hubness problem and accelerating model convergence. We conduct extensive experiments to evaluate the alignment performance of SCMEA. The overall experimental results, ablation studies, and analysis performed on five cross -lingual datasets demonstrate that our model achieves varying degrees of performance improvement and verifies the effectiveness and robustness of the model.

关键词:

Contrastive learning Representation learning Knowledge fusion Entity alignment Knowledge graph

作者机构:

  • [ 1 ] [Zhou, Yunfeng]Beijing Univ Technol, Fac Informat Technol, Beijing 100020, Peoples R China
  • [ 2 ] [Zhu, Cui]Beijing Univ Technol, Fac Informat Technol, Beijing 100020, Peoples R China
  • [ 3 ] [Zhu, Wenjun]Beijing Univ Technol, Fac Informat Technol, Beijing 100020, Peoples R China
  • [ 4 ] [Li, Hongyang]Beijing Univ Technol, Fac Informat Technol, Beijing 100020, Peoples R China

通讯作者信息:

  • [Zhu, Cui]Beijing Univ Technol, Fac Informat Technol, Beijing 100020, Peoples R China

查看成果更多字段

相关关键词:

来源 :

NEURAL NETWORKS

ISSN: 0893-6080

年份: 2024

卷: 173

7 . 8 0 0

JCR@2022

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 6

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:606/4948714
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