基于改进胶囊网络的文本分类

doi:10.11772/j.issn.1001-9081.2019122153

计算机应用 ›› 2020, Vol. 40 ›› Issue (9): 2525-2530.DOI: 10.11772/j.issn.1001-9081.2019122153

基于改进胶囊网络的文本分类

尹春勇, 何苗

南京信息工程大学计算机与软件学院, 南京 210044

收稿日期:2019-12-23 修回日期:2020-02-25 出版日期:2020-09-10 发布日期:2020-05-13
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）。

Text classification based on improved capsule network

YIN Chunyong, HE Miao

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).

摘要/Abstract

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

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

中图分类号:

TP391.1

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[J]. Journal of Computer Applications, 2020, 40(9): 2525-2530.

参考文献

[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.

基于改进胶囊网络的文本分类

Text classification based on improved capsule network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[2]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[3]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[4]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[5]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[6]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[7]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[8]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[9]	曾祥银, 郑伯川, 刘丹. 基于深度卷积神经网络和聚类的左右轨道线检测[J]. 计算机应用, 2021, 41(8): 2324-2329.
[10]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[11]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[12]	黄程程, 董霄霄, 李钊. 基于二维Winograd算法的深流水线5×5卷积方法[J]. 计算机应用, 2021, 41(8): 2258-2264.
[13]	武光利, 李雷霆, 郭振洲, 王成祥. 基于改进的双向长短期记忆网络的视频摘要生成模型[J]. 计算机应用, 2021, 41(7): 1908-1914.
[14]	谭道强, 曾诚, 乔金霞, 张俊. 基于混合注意力模型的阴影检测方法[J]. 计算机应用, 2021, 41(7): 2076-2081.
[15]	吴则举, 焦翠娟, 陈亮. 基于改进Faster R-CNN的轮胎缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1939-1946.