计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (13): 143-151.DOI: 10.3778/j.issn.1002-8331.2303-0380

• 模式识别与人工智能 • 上一篇    下一篇

一种面向关系抽取的表填充依赖特征学习方法

唐媛,陈艳平,扈应,黄瑞章,秦永彬   

  1. 1.贵州大学 文本计算与认知智能教育部工程研究中心,贵阳 550025
    2.贵州大学 公共大数据国家重点实验室,贵阳 550025
    3.贵州大学 计算机科学与技术学院,贵阳 550025
  • 出版日期:2024-07-01 发布日期:2024-07-01

Dependency Feature Learning Method for Table Filling for Relation Extraction

TANG Yuan, CHEN Yanping, HU Ying, HUANG Ruizhang, QIN Yongbin   

  1. 1.Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry, Guizhou University, Guiyang 550025, China
    2.State Key Laboratory of Public Big Data, Guizhou University, Guiyang 550025, China
    3.College of Computer Science and Technology, Guizhou University, Guiyang 550025, China
  • Online:2024-07-01 Published:2024-07-01

摘要: 基于表填充的关系抽取方法利用深度神经网络将句子映射到二维抽象表示,忽略了句子中不同跨度之间的语义结构,很难获取到句子中的长距离语义依赖。针对表填充方法的这一不足之处,提出了一个结合句法依存树的表填充关系抽取模型。该模型通过双仿射将句子映射到二维抽象表示。利用句子的句法依存树初始化语义依赖邻接矩阵,利用邻接矩阵学习二维表示中单词与单词之间的句法依赖特征。使用门控循环单元提取特征对句子的二维表示进行更新,从而在句子二维抽象表示中获取跨度之间的语义依赖关系和句子的结构特征。实验结果表明提出的模型可以有效获取句子中的长距离语义依赖特征,通过学习跨度的语义依赖信息和句子的语法结构特征来提升关系抽取的性能。

关键词: 关系抽取, 表填充, 句法依存树, 神经网络

Abstract: Table-filling-based relation extraction methods use deep neural networks to map sentences to two-dimensional abstract representations, ignoring the semantic structure between different spans in sentences, and it is difficult to obtain long-distance semantic dependencies in sentences. Aiming at this shortcoming of the table filling method, this paper proposes a table-filling relation extraction model combined with syntactic dependency tree. First, the model maps sentences to 2D abstract representations via biaffine. And then, the semantic dependency adjacency matrix is initialized through using the syntactic dependency tree of the sentence, whose features between words in the two-dimensional representation can be learned using the adjacency matrix. Finally, the 2D representation of the sentence is updated using gated recurrent unit extraction features to capture the semantic dependencies between spans and the structural features of the sentence in the sentence 2D abstract representation. Experimental results show that the proposed model can acquire long-distance semantic dependency features in sentences effectively, and improve the performance of relation extraction by learning span semantic dependency information and sentence grammatical structure features.

Key words: relation extraction, table filling, syntactic dependency tree, neural networks