基于改进胶囊网络的文本分类

doi:10.11772/j.issn.1001-9081.2019122153

摘要
图/表
参考文献(0)
相关文章 (15)

全文: PDF (952 KB) HTML
输出: BibTeX | EndNote (RIS)

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。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	尹春勇
	何苗

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

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

收稿日期: 2019-12-23 出版日期: 2020-05-13

中图分类号:

TP391.1

基金资助:国家自然科学基金资助项目（61772282）。

通讯作者: 尹春勇 E-mail: yinchunyong@hotmail.com

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。

引用本文:

尹春勇, 何苗. 基于改进胶囊网络的文本分类[J]. 计算机应用, 2020, 40(9): 2525-2530. YIN Chunyong, HE Miao. Text classification based on improved capsule network. Journal of Computer Applications, 2020, 40(9): 2525-2530.

链接本文:

http://www.joca.cn/CN/10.11772/j.issn.1001-9081.2019122153 或 http://www.joca.cn/CN/Y2020/V40/I9/2525

[1] 王艺颖. 朴素贝叶斯方法在中文文本分类中的应用[J]. 中国高新科技, 2019(7):57-60.(WANG Y Y. Application of naive Bayes method in Chinese text classification[J]. China High-Tech, 2019(7):57-60.)
[2] 钟磊. 基于贝叶斯分类器的中文文本分类[J]. 电子技术与软件工程, 2016(22):156-156.(ZHONG L. Chinese text classification based on Bayesian classifier[J]. Electronic Technology and Software Engineering, 2016(22):156-156.)
[3] 殷亚博,杨文忠,杨慧婷,等. 基于搜索改进的KNN文本分类算法[J]. 计算机工程与设计, 2018, 39(9):2923-2928.(YIN Y B, YANG W Z, YANG H T, et al. KNN text classification algorithm based on search improvement[J]. Computer Engineering and Design, 2018, 39(9):2923-2928.)
[4] LIU J, JIN T, PAN K, et al. An improved KNN text classification algorithm based on Simhash[C]//Proceedings of the IEEE 16th International Conference on Cognitive Informatics and Cognitive Computing. Piscataway:IEEE, 2017:92-95.
[5] 郭超磊,陈军华. 基于SA-SVM的中文文本分类研究[J]. 计算机应用与软件, 2019, 36(3):277-281.(GUO C L, CHEN J H. Chinese text classification based on SA-SVM[J]. Computer Applications and Software, 2019, 36(3):277-281.)
[6] 姚立,张曦煌. 基于主题模型的改进随机森林算法在文本分类中的应用[J]. 计算机应用与软件, 2017, 34(8):173-178, 212. (YAO L, ZHANG X H. Improved random forests algorithm based on topic model and its application in text classification[J]. Computer Application and Software, 2017, 34(8):173-178, 212.)
[7] WEI F, QIN H, YE S, et al. Empirical study of deep learning for text classification in legal document review[C]//Proceedings of the 2018 IEEE International Conference on Big Data. Piscataway:IEEE, 2018:3317-3320.
[8] HU F, LI L, ZHANG Z, et al. Emphasizing essential words for sentiment classification based on recurrent neural networks[J]. Journal of Computer Science and Technology, 2017, 32(4):785-795.
[9] 冯国明,张晓冬,刘素辉. 基于CapsNet的中文文本分类研究[J]. 数据分析与知识发现, 2019, 2(12):68-76.(FENG G M, ZHANG X D, LIU S H. Classifying Chinese texts with CapsNet[J]. Data Analysis and Knowledge Discovery, 2019, 2(12):68-76.)
[10] CHURCH K W. Word2Vec[J]. Natural Language Engineering, 2017, 23(1):155-162.
[11] 薛炜明,侯霞,李宁. 一种基于word2vec的文本分类方法[J]. 北京信息科技大学学报(自然科学版), 2018, 33(1):71-75.(XUE W M, HOU X, LI N. A text categorization method based on word2vec[J]. Journal of Beijing Information Science and Technology University, 2018, 33(1):71-75.)
[12] ZHAO W, YE J, YANG M, et al. Investigating capsule networks with dynamic routing for text classification[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA:Association for Computational Linguistics, 2018:3110-3119.
[13] HINTON G E, KRIZHEVSKY A, WANG S D. Transforming autoencoders[C]//Proceedings of the 21st International Conference on Artificial Neural Networks, LNCS 6791. Berlin:Springer, 2011:44-51.
[14] SABOUR S, FROSST N, HINTON G E. Dynamic routing between capsules[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, NY:Curran Associates Inc., 2017:3856-3866.
[15] 朱娟,陈晓. 改进胶囊网络的有序重叠手写数字识别方法[J]. 激光杂志, 2019, 40(7):43-46.(ZHU J, CHEN X. Improved capsule network for recognition of orderly overlapped handwritten numerals[J]. Laser Journal, 2019, 40(7):43-46.)
[16] 张天柱,邹承明. 使用模糊聚类的胶囊网络在图像分类上的研究[J]. 计算机科学, 2019, 46(12):279-285.(ZHANG T Z, ZOU C M. Study on image classification of capsule network using fuzzy clustering[J]. Computer Science, 2019, 46(12):279-285.)
[17] NOWAK J, TASPRINAR A, SCHERER R. LSTM recurrent neural networks for short text and sentiment classification[C]//Proceedings of the 16th International Conference on Artificial Intelligence and Soft Computing, LNCS 10246. Cham:Springer, 2017:553-562.