• 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:

Zhao, Yiran (Zhao, Yiran.) | Wu, Di (Wu, Di.) | Dai, Shuqi (Dai, Shuqi.) | Li, Tong (Li, Tong.)

收录:

CPCI-S EI Scopus

摘要:

Relation extraction is fundamental in knowledge graph construction. Recent studies have indicated the efficacy of Graph Convolutional Networks in enhancing performance in relation extraction tasks by leveraging dependency trees. However, noise in automatically generated dependency trees poses a challenge to using syntactic dependency information effectively. In this paper, we propose an Adaptive Graph Attention Network model based on Dependency Type and Direction information, which effectively reduces noise through direction-aware dependency relations, thereby enhancing extraction performance. Specifically, we propose an adaptive graph attention mechanism to construct direction-aware adjacency matrices for the precise aggregation of dependency pairs centred around entities as head words. This mechanism effectively filters out noise interference from entities acting as dependent words. Moreover, our model dynamically allocates weights to different dependency types based on their directions. This adaptive allocation enhances the learning capability of entity representations, optimizing the encoding and extraction of entity information. Experimental results on two English benchmark datasets demonstrate that introducing direction information significantly enhances the model's performance. These findings validate the efficacy of incorporating directionality in encoding to reduce dependency noise and improve relation extraction task performance.

关键词:

Relation extraction Adapted graph attention networks Directional information

作者机构:

  • [ 1 ] [Zhao, Yiran]Beijing Univ Technol, Beijing 100124, Peoples R China
  • [ 2 ] [Wu, Di]Beijing Univ Technol, Beijing 100124, Peoples R China
  • [ 3 ] [Dai, Shuqi]Beijing Univ Technol, Beijing 100124, Peoples R China
  • [ 4 ] [Li, Tong]Beijing Univ Technol, Beijing 100124, Peoples R China

通讯作者信息:

  • [Li, Tong]Beijing Univ Technol, Beijing 100124, Peoples R China

查看成果更多字段

相关关键词:

相关文章:

来源 :

DOCUMENT ANALYSIS AND RECOGNITION-ICDAR 2024, PT IV

ISSN: 0302-9743

年份: 2024

卷: 14807

页码: 287-305

被引次数:

WoS核心集被引频次:

SCOPUS被引频次:

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:551/4964076
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