Intelligent Text Classification Method Based on VAE-DBN Dual-Model

doi:10.3969/j.issn.1006-2475.2018.12.015

Abstract

Abstract: Text categorization technology is the foundation of information filtering, search engine and other fields, and is one of current research hot-spots. Based on the introduction of text classification related concepts and deep learning related models, this paper presents a dual-model text classification method based on the variational autoencoder model and the deep belief network model (VAE-DBN) by analyzing the shortcomings of the traditional text classification methods. By comparing and verifying the corpus, the results show that the dual-model method can effectively improve the accuracy of text categorization.

Key words: variational autoencoder, deep belief network, text categorization

CLC Number:

TP391

WANG Wei1,2. Intelligent Text Classification Method Based on VAE-DBN Dual-Model[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2018.12.015.

References

［1］ TAN P N, STEITBACH M, KUMAR V. 数据挖掘导论（中文版）［M］. 范明,范宏建,等译. 北京:人民邮电出版杜, 2011:139-141.
［2］周超. 基于深度学习混合模型的文本分类研究［D］. 兰州：兰州大学, 2016
［3］ COVER T, HART P. Nearest neighbor pattern classification［J］. IEEE Transactions on Information Theory, 1967,13(1):21-27.
［4］〖JP4〗WEBB G I, PAZZAN M J. Adjuated prohability naive Bayesian induction［C］// Proceedings of the 1lth Australian Joint Conference on Artificial Intelligence. 1998:285-295.
［5］赵中原. 基于神经网络的中文文本分类研究［D］. 南京：南京邮电大学， 2005.
［6］汪辉.侯传宇. 决策树相关算法研究［J］. 电脑知识与技术, 2011,7(15):3572-3574.
［7］李忠伟. 支持向量机学习算法研究［D］. 哈尔滨:哈尔滨工程大学, 2006.
［8］ YANG Z, YANG D, DYER C, et al. Hierarchical attention networks for document classification［C］// Proceedings of 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2017:1480-1489.
［9］ RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors［J］. Nature, 1986,323(6088):533-538.
［10］黄立威,江碧涛,吕守业,等. 基于深度学习的推荐系统研究综述［J］. 计算机学报, 2018(7), http://www.cnki.com.cn/Article/CJFDTotal-JSJX20180303003.htm.
［11］BENGIO Y, LAMBLIN P, POPOVICI D, et al. Greedy layer-wise training of deep networks［C］// Proceedings of the 19th International Conference on Neural Information Processing Systems. 2006:53-160.
［12］VINCENT P, LAROCHELLE H, BENGIOY. Extracting and composing robust features with denoising autoencoders［C］// Proceedings of the 25th International Conference on Machine Learning. 2008:1096-1103.
［13］HINTON G E, SEJNOWSKI T J. Learning and relearning in Boltzmann machines［J］. Parallel Distrilmted Processing, 1986,1:282-317.
［14］SMOLENSKY P. Information Processing in Dynamical Systems: Foundations of Harmony Theory［R］. University of Colorado, 1986.
［15］HINTON G E. A Practical Guide to Training Restricted Boltzmann Machines［M］. Springer Berlin Heidelberg, 2012:599-619.
［16］吕淑宝,王明月,翟祥,等. 一种深度学习的信息文本分类算法［J］. 哈尔滨工业大学学报, 2017,22(2):105-112.
［17］BENGIO Y. Learning deep architectures for AI［J］. Foundations & Trends in Machine Learning, 2009,2(1):1-127.
［18］陈翠平. 基于深度信念网络的文本分类算法［J］. 计算机系统应用, 2015,24(2):121-126.
［19］王明月. 基于深度学习的林业信息文本分类算法研究［D］. 沈阳:东北大学, 2017.
［20］LIU T. A novel text classification approach based on deep belief network［C］// Proceedings of Neural Information Processing Theory and Algorithms International Conference. 2010:314-321.
［21］翟文洁,闫琰,张博文,等. 基于混合深度信念网络的多类文本表示与分类方法［J］. 情报工程, 2016,2(5):30-40.
［22］王贵新,郑孝宗,张浩然,等. 利用深度置信网络的中文短信分类［J］. 现代电子技术, 2016,39(9):37-40.

[1]	LIU Fu-qi, ZHANG Da. PSO-DBN-based Hydraulic System Cooler Fault Diagnosis [J]. Computer and Modernization, 2023, 0(06): 7-14.
[2]	WU Jun-cai, LIU Xue-fang . Digital Resource Allocation Based on Cloud Computing and Deep Belief Network [J]. Computer and Modernization, 2021, 0(05): 78-82.