Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (7): 2011-2017.DOI: 10.11772/j.issn.1001-9081.2023081183

• Artificial intelligence • Previous Articles     Next Articles

Relation extraction model based on multi-scale hybrid attention convolutional neural networks

Yuan TANG1,2,3, Yanping CHEN1,2,3(), Ying HU1,2,3, Ruizhang HUANG1,2,3, Yongbin QIN1,2,3   

  1. 1.Text Computing and Cognitive Intelligence Engineering Research Center of Ministry of Education,Guizhou University,Guiyang Guizhou 550025,China
    2.State Key Laboratory of Public Big Data (Guizhou University),Guiyang Guizhou 550025,China
    3.College of Computer Science and Technology,Guizhou University,Guiyang Guizhou 550025,China
  • Received:2023-09-03 Revised:2023-10-13 Accepted:2023-10-17 Online:2024-07-18 Published:2024-07-10
  • Contact: Yanping CHEN
  • About author:TANG Yuan, born in 1999, M. S. candidate. Her research interests include natural language processing, information extraction.
    HU Ying, born in 1996, Ph. D. candidate. His research interests include natural language processing.
    HUANG Ruizhang, born in 1979, Ph. D., professor. Her research interests include big data and data mining, information extraction.
    QIN Yongbin, born in 1980, Ph. D., professor. His research interests include big data management and application, multi-source data fusion and application.
    First author contact:CHEN Yanping, born in 1980, Ph. D., professor. His research interests include artificial intelligence, natural language processing.
  • Supported by:
    National Natural Science Foundation of China(62166007);Key Technology Research and Development Program of Guizhou Province([2022]277)

基于多尺度混合注意力卷积神经网络的关系抽取模型

唐媛1,2,3, 陈艳平1,2,3(), 扈应1,2,3, 黄瑞章1,2,3, 秦永彬1,2,3   

  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.公共大数据国家重点实验室(贵州大学), 贵阳 550025
    3.贵州大学 计算机科学与技术学院, 贵阳 550025
  • 通讯作者: 陈艳平
  • 作者简介:唐媛(1999—),女,四川遂宁人,硕士研究生,主要研究方向:自然语言处理、信息抽取;
    扈应(1996—),男,重庆人,博士研究生,主要研究方向:自然语言处理;
    黄瑞章(1979—),女,天津人,教授,博士,CCF会员,主要研究方向:大数据与数据挖掘、信息提取;
    秦永彬(1980—),男,山东烟台人,教授,博士,CCF高级会员,主要研究方向:大数据管理与应用、多源数据融合与应用。
    第一联系人:陈艳平(1980—),男,贵州长顺人,教授,博士,CCF会员,主要研究方向:人工智能、自然语言处理;
  • 基金资助:
    国家自然科学基金资助项目(62166007);贵州省科技支撑计划项目([2022]277)

Abstract:

To address the issue of insufficient extraction of semantic feature information with different scales and the lack of focus on crucial information when obtaining sentence semantic information by Convolutional Neural Network (CNN)-based relation extraction, a model for relation extraction based on a multi-scale hybrid attention CNN was proposed. Firstly, relation extraction was modeled as label prediction with two-dimensional representation. Secondly, by extracting and fusing multi-scale feature information, finer-grained multi-scale spatial information was obtained. Thirdly, through the combination of attention and convolution, the feature maps were refined adaptively to make the model concentrate on important contextual information. Finally, two predictors were used jointly to predict the relation labels between entity pairs. Experimental results demonstrate that the multi-scale hybrid convolutional attention model can capture multi-scale semantic feature information,And the key information in channels and spatial locations was captured by the channel attention and spatial attention by assigning appropriate weights, thereby improving the performance of relation extraction. The proposed model achieves F1 scores of 90.32% on SemEval (SemEval-2010 task 8) dataset, 70.74% on TACRED (TAC Relation Extraction Dataset), 85.71% on Re-TACRED (Revised-TACRED), and 89.66% on SciERC (Entities, Relations, and Coreference for Scientific knowledge graph construction).

Key words: relation extraction, two-dimensional representation, channel attention, spatial attention, multi-scale semantic feature

摘要:

针对基于卷积神经网络(CNN)的关系抽取获取句子语义信息时缺少不同尺度语义特征信息的获取以及对关键信息的关注的问题,提出基于多尺度混合注意力CNN的关系抽取模型。首先,将关系抽取建模为二维化表示的标签预测;其次,通过多尺度的特征信息提取与融合,获得更细粒度的多尺度空间信息;然后,通过注意力与卷积的结合自适应地细化特征图,使模型关注重要的上下文信息;最后,使用两个预测器共同预测实体对之间的关系标签。实验结果表明,多尺度混合卷积注意力模型能够获取多尺度语义特征信息,而通道注意力和空间注意力通过权重捕捉通道和空间的关键信息,以此来提升关系抽取的性能。所提模型在数据集SemEval (SemEval-2010 task 8)、TACRED (TAC Relation Extraction Dataset)、Re-TACRED (Revised-TACRED)和SciERC (Entities, Relations, and Coreference for Scientific knowledge graph construction)上的F1值分别达到90.32%、70.74%、85.71%和89.66%。

关键词: 关系抽取, 二维化表示, 通道注意力, 空间注意力, 多尺度语义特征

CLC Number: