基于卷积神经网络的中文财经新闻分类方法

doi:10.6040/j.issn.1672-3961.0.2017.433

山东大学学报(工学版) ›› 2018, Vol. 48 ›› Issue (3): 34-39.doi: 10.6040/j.issn.1672-3961.0.2017.433

基于卷积神经网络的中文财经新闻分类方法

谢志峰^1,2,吴佳萍¹,马利庄^2,3

1. 上海大学影视工程系, 上海 200072;2. 上海电影特效工程技术研究中心, 上海 200072;3. 上海交通大学计算机科学与工程系, 上海 200240

收稿日期:2017-08-29 出版日期:2018-06-20 发布日期:2017-08-29
作者简介:谢志峰(1982— ),男,江苏如东人,博士,讲师,主要研究领域为信息处理、深度学习等. E-mail:zhifeng_-xie@shu.edu.cn
基金资助:
国家自然科学基金资助项目(61303093,61402278,61472245);上海市科委科技攻关资助项目(16511101300)

Chinese financial news classification method based on convolutional neural network

XIE Zhifeng^1,2, WU Jiaping¹, MA Lizhuang^2,3

1. Department of Film and Television Engineering, Shanghai University, Shanghai 200072, China;
2. Shanghai Engineering Research Center of Motion Picture Special Effects, Shanghai 200072, China;
3. Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai 200240, China

Received:2017-08-29 Online:2018-06-20 Published:2017-08-29

摘要/Abstract

摘要： 针对目前财经领域内新闻数据杂乱无章、缺乏自动高效管理等问题,提出一种基于卷积神经网络的中文财经新闻分类方法。收集大规模财经新闻语料,通过无监督学习方法训练获得一个广义通用的财经类词向量模型,将词向量引入到卷积神经网络模型训练中实现有效分类。与传统方法相比,基于卷积神经网络的中文财经新闻分类方法网络模型结构简单,针对小样本集也能表现优异的性能,不仅能有效解决中文财经新闻分类问题,还可充分证明卷积神经网络在处理文本分类问题中的有效性。

关键词: 财经新闻, 卷积神经网络, 词向量, 自然语言处理, 深度学习, 文本分类

Abstract: In order to complete the task of financial news classification, a new method based on convolutional neural network for the classification of Chinese financial news was presented. A simple CNN was trained with one layer of convolution on top of word vectors obtained from an unsupervised neural language model. These vectors were trained on a large number of financial news corpus. Compared with the traditional methods, the network model based on convolutional neural network was simple in structure, which could show excellent performance by using small sample set. The method not only could solve the Chinese financial news classification problem effectively, but also prove the effectiveness of convolutional neural network in dealing with problems of text classification fully.

Key words: financial news, convolutional neural network, natural language processing, deep learning, word vector, text classification

中图分类号:

TP391.1

谢志峰,吴佳萍,马利庄. 基于卷积神经网络的中文财经新闻分类方法[J]. 山东大学学报(工学版), 2018, 48(3): 34-39.

XIE Zhifeng, WU Jiaping, MA Lizhuang. Chinese financial news classification method based on convolutional neural network[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2018, 48(3): 34-39.

参考文献

[1] WANG S, MANNING C D. Baselines and bigrams: Simple, good sentiment and topic classification[C] //Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics. Jeju Island, Korea: ACL, 2012: 90-94.
[2] KRIZHEVSKY A, SUTSKEVER I, HINTON G. Imagenet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012, 60(2): 1097-1105.
[3] SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C] //Proceedings of Conference on Computer Vision and Pattern Recognition(CVPR). Boston, USA: IEEE, 2015: 1-9.
[4] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2017-06-20]. https://arxiv.org/pdf/1409.1556v6.pdf.
[5] 徐姗姗, 刘应安, 徐昇. 基于卷积神经网络的木材缺陷识别[J]. 山东大学学报(工学版), 2013, 43(2): 23-28. XU Shanshan, LIU Ying'an, XU Sheng. Wood defects recognition based on the convolutional neural network[J]. Journal of Shandong University(Engineering Science), 2013, 43(2): 23-28.
[6] 奚雪峰, 周国栋. 面向自然语言处理的深度学习研究[J]. 自动化学报, 2016, 42(10): 1445-1565. XI Xuefeng, ZHOU Guodong. A survey on deep learning for natural language processin[J]. Acta Automatica Sinica, 2016, 42(10): 1445-1565.
[7] BENGIO Y, DUCHARME R, VINCENT P, et al. A neural probabilistic language model[J]. The Journal of Machine Learning Research, 2006, 3(6):1137-1155.
[8] FISCHER A, IGEL C. An introduction to restricted Boltzmann machines[C] //Iberoamerican Congress on Pattern Recognition. Berlin, Germany: Springer, 2012: 14-36.
[9] MNIH A, HINTON G. A scalable hierarchical distributed language model[C] //International Conference on Neural Information Processing Systems. Vancouver, Canada: NIPS, 2008: 1081-1088.
[10] SOCHER R, PENNINGTON J, HUANG E H, et al. Semi-supervised recursive autoencoders for predicting sentiment distributions[C] //Proceedings of the Conference on Empirical Methods in Natural Language Processing. Edinburgh, Britain: ACL, 2011: 151-161.
[11] COLLOBERT R, WESTON J,BOTTOU L, et al. Natural language processing(almost)from scratch[J]. The Journal of Machine Learning Rearch, 2011, 12(1): 2493-2537.
[12] MIOLOV T, SUTSKEVER I, CHEN K, et al. Distributed representations of words and phrases and their compositionality[C] //Proceedings of the 26th International Conference on Neural Information Processing Systems. Lake Tahoe, USA: NIPS, 2013: 3111-3119.
[13] ZHOU Shusen, CHEN Qingcai, WANG Xiaolong. Convolutional active deep learning method for semi-supervised sentiment classification[J]. Necuro computing, 2013, 120(10): 536-546.
[14] JOHNSON R, ZHANG T. Effective use of word order for text categorization with convolutional neural networks[J]. Eprint Arxiv, 2014:1412.
[15] BLUNSOM P, GREFENSTEEN E, KALCHBRENNER N. et al. Aconovolutional neural network for modelling sentences[C] //Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics. Baltimore, USA: ACL, 2014: 655-665.
[16] KIM Y. Convolutional neural networks for sentence classification[C] //Proceedings of the EMNLP. Doha, Qatar: Association for Computational Linguistics, 2014: 1746-1751.
[17] MIKOLOV T, CHEN K, CORRADO G, et al. Efficient estimation of word representations in vector space[EB/OL]. [2017-06-20]. https://arxiv.org/pdf/1301.3781v3.pdf
[18] HINTON G E, SRIVASTAVA N, KRIZHEVSKY A, et al. Improving neural networks by preventing co-adaptation of feature detectors[EB/OL]. [2017-06-20]. https://arxiv.org/pdf/1207.0580v1.pdf.
[19] 唐明,朱磊,邹显春. 基于Word2vec的一种文档向量表示[J]. 计算机科学,2016, 43(6): 264-269. TANG Ming, ZHU Lei, ZOU Xianchun, et al. Documenl vector representation based on Word2vec[J]. Computer Science, 2016, 43(6): 264-269.
[20] 陈钊,徐睿峰,桂林,等. 结合卷积神经网络和词语情感序列特征的中文情感分析[J]. 中文信息学报, 2015, 29(6): 172-178. CHEN Zhao, XU Ruifeng, GUI Lin, et al. Combining convolutional neural networks and word sentiment sequence features for Chinese text sentiment analysis[J]. Processing of Journal of chinese Imformation, 2015, 29(6): 172-178.
[21] ZEILER M. ADADELTA: An adaptive learning rate method[EB/OL]. [2017-06-20]. https://arxiv.org/pdf/1212.5701v1.pdf.
[22] BOTTOU L. Large-scale machine learning with stochastic gradient descent[C] //Proceedings of COMPATAT’2010. Berlin, Germany: Springer, 2010: 177-186.
[23] SOCHER B, HUVAL C, MANNING A. Semantic compositionality through recursive matrix-vector spaces[C] //Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Jeju Island, Korea: ACL, 2012: 1201-1211.
[24] DONG L, LIU S J, ZHOU M, et al. A statistical parsing framework for sentiment classification[J]. Computational Linguistic, 2015, 41(2): 293-336.
[25] NAKAGAWA K, INUI S, KUROHASHI S. Dependency tree-based sentiment classification using CRFs with hidden variables[C] //The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics. Los Angeles, USA: ACL, 2010: 786-794.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于卷积神经网络的中文财经新闻分类方法

Chinese financial news classification method based on convolutional neural network

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

多维度评价

本文评价

推荐阅读 0

[1]	张璞,刘畅,王永. 基于特征融合和集成学习的建议语句分类模型[J]. 山东大学学报(工学版), 2018, 48(5): 47-54.
[2]	梁蒙蒙,周涛,夏勇,张飞飞,杨健. 基于PSO-ConvK卷积神经网络的肺部肿瘤图像识别[J]. 山东大学学报(工学版), 2018, 48(5): 77-84.
[3]	赵彦霞, 王熙照. 基于SVD和DCNN的彩色图像多功能零水印算法[J]. 山东大学学报(工学版), 2018, 48(3): 25-33.
[4]	何正义,曾宪华,郭姜. 一种集成卷积神经网络和深信网的步态识别与模拟方法[J]. 山东大学学报(工学版), 2018, 48(3): 88-95.
[5]	唐乐爽,田国会,黄彬. 一种基于DSmT推理的物品融合识别算法[J]. 山东大学学报(工学版), 2018, 48(1): 50-56.
[6]	周福娜,高育林,王佳瑜,文成林. 基于深度学习的缓变故障早期诊断及寿命预测[J]. 山东大学学报(工学版), 2017, 47(5): 30-37.
[7]	何正义,曾宪华,曲省卫,吴治龙. 基于集成深度学习的时间序列预测模型[J]. 山东大学学报(工学版), 2016, 46(6): 40-47.
[8]	郑毅, 朱成璋. 基于深度信念网络的PM_2.5预测[J]. 山东大学学报(工学版), 2014, 44(6): 19-25.
[9]	徐姗姗,刘应安*,徐昇. 基于卷积神经网络的木材缺陷识别[J]. 山东大学学报(工学版), 2013, 43(2): 23-28.
[10]	张永军1,刘金岭2,于长辉3. 基于词贡献度的垃圾短信分类方法[J]. 山东大学学报(工学版), 2012, 42(5): 87-90.
[11]	王洪元,封磊,冯燕,程起才. 流形学习算法在中文文本分类中的应用[J]. 山东大学学报(工学版), 2012, 42(4): 8-12.
[12]	王法波,许信顺. 文本分类中一种新的特征选择方法[J]. 山东大学学报(工学版), 2010, 40(4): 8-11.
[13]	董乃鹏赵合计 SCHOMMER Christoph. 作者写作特征提取引擎[J]. 山东大学学报(工学版), 2009, 39(5): 27-31.