基于TNG特征扩展的MLFM-MN短文本分类算法

计算机工程与科学

基于TNG特征扩展的MLFM-MN短文本分类算法

文武1,2,3，李培强1,2，郭有庆1,2

（1.重庆邮电大学通信与信息工程学院，重庆 400065；

2.重庆邮电大学通信新技术应用研究中心，重庆 400065；3.重庆信科设计有限公司，重庆 401121）

收稿日期:2018-12-11 修回日期:2019-04-25 出版日期:2019-11-25 发布日期:2019-11-25

An MLFM-MN short text classification

algorithm based on TNG feature extension

WEN Wu1,2,3，LI Pei-qiang1,2，GUO You-qing1,2

（1.School of Communication and Information Engineering,
Chongqing University of Posts and Telecommunications,Chongqing 400065;

2.Research Center of New Communication Technology Applications,

Chongqing University of Posts and Telecommunications,Chongqing 400065;

3.Chongqing Xinke Design Co.Ltd.,Chongqing 401121,China）

Received:2018-12-11 Revised:2019-04-25 Online:2019-11-25 Published:2019-11-25

摘要/Abstract

摘要：

在海量短文本中由于特征稀疏、数据维度高这一问题，传统的文本分类方法在分类速度和准确率上达不到理想的效果。针对这一问题提出了一种基于Topic N-Gram（TNG）特征扩展的多级模糊最小-最大神经网络（MLFM-MN）短文本分类算法。首先通过使用改进的TNG模型构建一个特征扩展库并对特征进行扩展，该扩展库不仅可以推断单词分布，还可以推断每个主题文本的短语分布；然后根据短文本中的原始特征，计算这些文本的主题倾向，根据主题倾向，从特征扩展库中选择适当的候选词和短语，并将这些候选词和短语放入原始文本中；最后运用MLFM-MN算法对这些扩展的原始文本对象进行分类，并使用精确率、召回率和F1分数来评估分类效果。实验结果表明，本文提出的新型分类算法能够显著提高文本的分类性能。

关键词: 特征稀疏, TNG模型, 模糊神经网络, 扩展库, 主题倾向

Abstract:

Due to the problems of sparse features and high data dimension in short text, traditional text classification methods cannot achieve the desired classification rate and accuracy. Aiming at this problem, we propose a multi-level fuzzy minimum and maximum neural network (MLFM-MN) short text classification algorithm based on topic N-Gram (TNG) feature extension. The algorithm first constructs a feature extension library and extends the features by using the improved TNG model. The extension library can not only infer the word distribution, but also infer the phrase distribution of each topic text, and then calculate these based on the original features in the short text. Appropriate candidate words and phrases are selected from the feature extension library according to topic tendencies, and put into the original text. Finally, the extended text objects are classified by the MLFM-MN algorithm. We use accuracy rate, recall rate and F1 score to evaluate the classification effect. The results show that the proposed algorithm can significantly improve text classification performance.

Key words: sparse feature, TNG model, fuzzy neural network, extension library, topic tendency

文武1,2,3，李培强1,2，郭有庆1,2. 基于TNG特征扩展的MLFM-MN短文本分类算法[J]. 计算机工程与科学.

WEN Wu1,2,3，LI Pei-qiang1,2，GUO You-qing1,2.

An MLFM-MN short text classification

algorithm based on TNG feature extension

[J]. Computer Engineering & Science.

参考文献［20］

［1］	Wang B K,Huang Y F,Yang W X,et al.Short text classification based on strong feature thesaurus［J］.Journal of Zhejiang University Science
	(Computer & Electronics)
	,2012,13(9):649-659.
［2］	Wang M, Lin L F, Wang J, et al.Improving short text classification using public search engines［C］∥
	Proc of the 2013 International Conference on Integrated Uncertainty in Knowledge Modelling and Decision Making,2013:157-166.
［3］	Sun A.Short text classification using very few words［C］∥Proc of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval,
20	12:1145-1146.
［4］	Zhang X,Wu B.Short text classification based on feature extension using the n-gram model［C］∥Proc of International Conference on Fuzzy Systems and Knowledge Discovery,2015:15-17.
［5］	Zhang Y,Jin R,Zhou Z H.Understanding bag-of-words model:A statistical framework［J］.International Journal of Machine Learning and Cybernetics,2010,1(1-4):43-52.
［6］	Zhang Lei.The research summary of text categorization and classification algorithms［J］.Computer Knowledge and Technology,2016,12(34):225-226.(in Chinese)
［7］	Liu Jing, Jiang Wen-bo,Shao Ye.Research progress of text classification technology based on machine learning［J］.Computer Fan,2018(6):26.(in Chinese)
［8］	Miao Y Q,Kamel M.Pairwise optimized rocchio algorithm for text categorization［J］.Pattern Recognition Letters,2011,32(2):375-382.
［9］	Patil T R, Sherekar S S.Performance analysis of naive bayes and J48 classification algorithm for data classification［J］. International Journal of Computer Science and Applications,2013,6(2):256-261.
［10］	Tong S, Koller D.Support vector machine active learning with applications to text classification［J］.Journal of Machine Learning Research,2002,2:45-66.
［11］	Deng Z,Zhu X,Cheng D,et al.Efficient knn classification algorithm for big data［J］.Neurocomputing,2016,195:143-148.
［12］	Taravat A, Frate F D, Cornaro C,et al.Neural networks and support vector machine algorithms for automatic cloud classification of whole-sky ground-based images［J］.IEEE Geoscience and Remote Sensing Letters,2015,12(3):666-670.
［13］	Ghareb A S,Bakar A A,Hamdan A R.Hybrid feature selection based on enhanced genetic algorithm for text categorization［J］.Expert Systems with Applications,2016,49:31-47.
［14］	Sun B,Zhao P.Feature extension for Chinese short text classification based on topical N-Grams［C］∥Proc of 2017 IEEE/ACIS 16th International Conference on Computer and Information Science (ICIS), 2017:477-482.
［15］	Wang X R,Mccallum A,Wei X.Topical n-grams:Phrase and topic discovery,with an application to information retrieval［C］∥Proc of the 2007 7th IEEE International Conference on Data Mining,2007:697-702.
［16］	Fan Yun-jie,Liu Huai-liang.Research on Chinese short text classification based on wikipedia［J］.Data Analysis and Knowledge Discovery,2012,28(3):47-52.(in Chinese)
［17］	Shirakawa M,Nakayama K,Hara T,et al.Wikipedia-based semantic similarity measurements for noisy short texts using extended naive bayes［J］.IEEE Transactions on Emerging Topics in Computing,2015,3(2):205-219.
［18］	Simpson P K.Fuzzy min-max neural networks.I.Classification［J］.IEEE Transactions on Neural Networks,1992,3(5):776-786.
［19］	Davtalab R,Dezfoulian M H,Mansoorizadeh M.Multi-level fuzzy min-max neural network classifier［J］.IEEE Transactions on Neural Networks and Learning Systems,2014,25(3):470-482.
［20］	Xue Tao,Wang Ya-ling,Mu Nan. Convolutional neural network based on word sense disambiguation for text classification［J］.Journal of Computer Applications,2018,35(10):2898-2903.(in Chinese)
［21］	Lilleberg J,Zhu Yun,Zhang Yan-qing.Support vector machines and word2vec for text classification with semantic features［C］∥Proc of 2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI* CC),2015:136-140.
［22］	Chen K,Zhang Z,Long J,et al.Turning from TF-IDF to TF-IGM for term weighting in text classification［J］.Expert Systems with Applications,2016,66:245-260.
	附中文参考文献：
［6］	张磊.文本分类及分类算法研究综述［J］.电脑知识与技术,
20	16,12(34):225-226.
［7］	刘婧,姜文波,邵野.基于机器学习的文本分类技术研究进展［J］.电脑迷,2018(6):26.
［16］	范云杰，刘怀亮.基于维基百科的中文短文本分类研究［J］.数据分析与知识发现，2012,28(3):47-52.
［20］	薛涛,王雅玲,穆楠.基于词义消歧的卷积神经网络文本分类模型［J］.计算机应用研究,2018,35(10):2898-2903.

[1]	黄保华1，莫家威2，吕琦1. 基于模糊神经网络的稳定AODV协议改进方案[J]. 计算机工程与科学, 2018, 40(11): 1974-1982.
[2]	李克文，张郁，马竟峰，刘洪太. 基于模糊三角数模糊神经网络的软件质量评价方法[J]. J4, 2014, 36(07): 1301-1306.
[3]	马莉, 张德丰, 许勇. 基于动态模糊神经网络的生物工程算法研究[J]. J4, 2010, 32(3): 137-140.
[4]	匡雁群李孝安. 基于模糊神经网络的机器人足球团队决策研究[J]. J4, 2008, 30(4): 145-147.
[5]	蔡镜[1] 陈晓[2] 包元晖[2]. 基于模糊神经网络的单兵装备效能评估专家系统[J]. J4, 2005, 27(6): 98-101.
[6]	吴小俊[1] 杨静宇[2] 王士同[1] 刘同明[1]. 基于模糊神经网络的人脸识别方法研究[J]. J4, 2004, 26(4): 36-38.