Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (9): 2525-2530.DOI: 10.11772/j.issn.1001-9081.2019122153

• Artificial intelligence • Previous Articles     Next Articles

Text classification based on improved capsule network

YIN Chunyong, HE Miao   

  1. School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing Jiangsu 210044, China
  • Received:2019-12-23 Revised:2020-02-25 Online:2020-09-10 Published:2020-05-13
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61772282).

基于改进胶囊网络的文本分类

尹春勇, 何苗   

  1. 南京信息工程大学 计算机与软件学院, 南京 210044
  • 通讯作者: 尹春勇
  • 作者简介:尹春勇(1977-),男,山东潍坊人,教授,博士生导师,博士,主要研究方向:网络空间安全、大数据挖掘、隐私保护、人工智能、新型计算;何苗(1995-),女,江苏淮安人,硕士研究生,主要研究方向:机器学习、数据挖掘、文本分类。
  • 基金资助:
    国家自然科学基金资助项目(61772282)。

Abstract: In order to solve the problems that the pooling operation of Convolutional Neural Network (CNN) will lose some feature information and the classification accuracy of Capsule Network (CapsNet) is not high, an improved CapsNet model was proposed. Firstly, two convolution layers were used to extract local features of feature information. Then, the CapsNet was used to extract the overall features of text. Finally, the softmax classifier was used to perform the classification. Compared with CNN and CapsNet, the proposed model improves the classification accuracy by 3.42 percentage points and 2.14 percentage points respectively. The experimental results show that the improved CapsNet model is more suitable for text classification.

Key words: text classification, Convolution Neural Network (CNN), Capsule Network (CapsNet), dynamic routing, feature extraction

摘要: 针对卷积神经网络(CNN)中的池化操作会丢失部分特征信息和胶囊网络(CapsNet)分类精度不高的问题,提出了一种改进的CapsNet模型。首先,使用两层卷积层对特征信息进行局部特征提取;然后,使用CapsNet对文本的整体特征进行提取;最后,使用softmax分类器进行分类。在文本分类中,所提模型比CNN和CapsNet在分类精度上分别提高了3.42个百分点和2.14个百分点。实验结果表明,改进CapsNet模型更适用于文本分类。

关键词: 文本分类, 卷积神经网络, 胶囊网络, 动态路由, 特征提取

CLC Number: