• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 计算机网络与信息安全 • 上一篇    下一篇

基于注意力机制的混合神经网络关系分类方法

庄传志1,2,靳小龙1,2,李忠1,2,孙智1,2   

  1. (1.中国科学院计算技术研究所网络数据科学与技术重点实验室,北京,100190;
    2.中国科学院大学计算机与控制学院,北京 100049)

     
  • 收稿日期:2019-07-10 修回日期:2019-09-17 出版日期:2020-01-25 发布日期:2020-01-25
  • 基金资助:

    国家重点研发计划(2016YFB1000902);国家自然科学基金(61772501,61572473,61572469,91646120)

An attention-based hybrid neural network
 relation classification method

ZHUANG Chuan-zhi1,2,JIN Xiao-long1,2,LI Zhong1,2,SUN Zhi1,2   

  1. (1.CAS Key Laboratory of Network Data Science and Technology,Institute of Computing Technology,
    Chinese Academy of Sciences,Beijing 100190;
    2.School of Computer and Control Engineering,University of Chinese Academy of Sciences,Beijing 100049,China)
  • Received:2019-07-10 Revised:2019-09-17 Online:2020-01-25 Published:2020-01-25

摘要:

关系分类是自然语言处理领域的一项重要语义处理任务。传统的关系分类方法通过人工设计各类特征以及各类核函数来对句子内部2个实体之间的关系进行判断。近年来,关系分类方法的主要工作集中于通过各类神经网络获取句子的语义特征表示来进行分类,以减少手动构造各类特征。在句子中,不同关键词对关系分类任务的贡献程度是不同的,然而重要的词义有可能出现在句子中的任意位置。为此,提出了一种基于注意力的混合神经网络关系分类模型来捕获重要的语义信息,用来进行关系分类,该方法是一种端到端的方法。实验结果表明了该方法的有效性。

 

关键词: 关系分类, 卷积神经网络, 长短时记忆网络, 注意力机制

Abstract:

Relation classification is an important semantic processing task in the field of natural language processing. The traditional relation classification method judges the relationship between two entities within a sentence by manually designing various features and various kernel functions. In recent years, the main work of the relation classification methods has focused on obtaining semantic feature representations of sentences through various neural networks to perform classification, so as to reduce the manual construction of various features. In sentences, the contribution of different keywords to the relation classification tasks are different, but the most important word meanings may appear at any position in the sentences. To this end, we propose an attention-based hybrid neural network relation classification method to capture the important semantic information for relation classification. This method is an end-to-end method. Experimental results show the effectiveness of the method.
 

Key words: relation classification, convolutional neural network, long short-term memory network, attention mechanism