[1]张 千,王庆玮,张 悦,等.基于深度学习的文本特征提取研究综述[J].计算机技术与发展,2019,29(12):61-65.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 011]
　ZHANG Qian,WANG Qing-wei,ZHANG Yue,et al.Review of Text Feature Extraction Based on Deep Learning[J].,2019,29(12):61-65.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 011]
点击复制

基于深度学习的文本特征提取研究综述()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年12期
页码:
61-65
栏目:
智能、算法、系统工程
出版日期:
2019-12-10

文章信息/Info

Title:
Review of Text Feature Extraction Based on Deep Learning
文章编号:
1673-629X(2019)12-0061-05
作者:
张 千; 王庆玮; 张 悦; 纪校锋; 张宇翔; 祝 赫; 赵昌志
中国石油大学(华东) 计算机与通信工程学院,山东 青岛 266580
Author(s):
ZHANG Qian; WANG Qing-wei; ZHANG Yue; JI Xiao-feng; ZHANG Yu-xiang; ZHU He; ZHAO Chang-zhi
School of Computer &Communication Engineering,China University of Petroleum (East China),Qingdao 266580,China
关键词:
深度学习; 特征提取; 文本特征; 自然语言处理; 文本挖掘
Keywords:
deep learning; feature extraction; text characteristic; natural language processing; text mining
分类号:
TP31
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 12. 011
摘要:
文本特征项的选择是文本挖掘和信息检索的基础和重要内容。 传统的特征提取方法需要手工制作的特征,而手工设计有效的特征是一个漫长的过程,但针对新的应用深度学习能够快速地从训练数据中获取新的有效特征表示。 作为一种新的特征提取方法,深度学习在文本挖掘方面取得了一定的成果。 深度学习与传统方法的主要区别在于,深度学习能自动地从大数据中学习特征而不是采用手工制作的特征,手工制作的特征主要依赖于设计者的先验知识,很难充分利用大数据;深度学习可以自动地从大数据中学习特征表示,并包括数以万计的参数。 文中概述了用于文本特征提取的常用方法,并阐述了在文本特征提取及应用中常用的深度学习方法,以及深度学习在特征提取中的应用展望。
Abstract:
The selection of text feature items is basic and important in text mining and information retrieval. Traditional feature extraction methods require hand-made features,and manual design of effective features is a long process. However,for new applications,deep learning can quickly obtain new and effective feature representation from training data. As a new feature extraction method,deep learning has made some achievements in text mining. The main difference between deep learning and traditional methods is deep learning can automatically learn features from large data rather than using hand-made features. Hand-made features mainly rely on designer’s prior knowledge,which is difficult to fully use large data. Deep learning can automatically learn feature representation from large data and include tens of thousands of parameters. We summarize the common methods of text feature extraction and expound the deep learning methods commonly used in text feature extraction and application,as well as the application prospect of depth learning in feature extraction.

相似文献/References:

[1]田昕辉 李成基.带有短语切分的中文文本分类方法[J].计算机技术与发展,2010,(01):5.
　TIAN Xin-hui,LEE Sung-kee.Phrase Segmentation for Chinese Text Classification[J].,2010,(12):5.
[2]何小娜 逄焕利.基于二维直方图和改进蚁群聚类的图像分割[J].计算机技术与发展,2010,(03):128.
　HE Xiao-na,PANG Huan-li.Image Segmentation Based on Improved Ant Colony Clustering and Two- Dimensional Histogram[J].,2010,(12):128.
[3]罗林波 陈绮.氨基酸序列特征提取方法研究[J].计算机技术与发展,2010,(02):206.
　LUO Lin-bo,CHEN Qi.Research of Feature Extraction Methods of Amino Acid Sequence[J].,2010,(12):206.
[4]姜鹤 陈丽亚.SVM文本分类中一种新的特征提取方法[J].计算机技术与发展,2010,(03):17.
　JIANG He,CHEN Li-ya.A New Feature Selection Method in SVM Text Categorization[J].,2010,(12):17.
[5]毛雁明 兰美辉 王运琼 冯乔生.一种改进的基于Harris的角点检测方法[J].计算机技术与发展,2009,(05):130.
　MAO Yan-ming,LAN Mei-hui,WANG Yun-qiong,et al.An Improved Corner Detection Method Based on Harris[J].,2009,(12):130.
[6]赵辉 张鹏.网络异常的主动检测与特征分析[J].计算机技术与发展,2009,(08):159.
　ZHAO Hui,ZHANG Peng.Active Detection and Feature Analysis About Network Anomaly[J].,2009,(12):159.
[7]汤婷 吴小培 项明.指纹图像增强与特征提取[J].计算机技术与发展,2009,(01):81.
　TANG Ting,WU Xiao-pei,XIANG Ming.Fingerprint Image Enhancement and Minutiae Extraction[J].,2009,(12):81.
[8]张国富 凌捷 彭辉 谷保平.基于支持向量机的手写签名研究[J].计算机技术与发展,2008,(05):57.
　ZHANG Guo-fu,LING Jie,PENG Hui,et al.Research of Handwritten Signature Based on SVM[J].,2008,(12):57.
[9]黄国宏 刘刚.一种新的基于Fisher准则的线性特征提取方法[J].计算机技术与发展,2008,(05):227.
　HUANG Guo-hong,LIU Gang.A New Linear Feature Extraction Method Based on Fisher Criterion[J].,2008,(12):227.
[10]黄国宏 刘刚.一种新的基于DCT变换的线性判别分析[J].计算机技术与发展,2008,(06):97.
　HUANG Guo-hong,LIU Gang.A Novel Linear Discriminant Analysis Based on DCT[J].,2008,(12):97.
[11]陈浩翔,蔡建明,刘铿然,等. 手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(07):19.
　CHEN Hao-xiang,CAI Jian-ming,LIU Keng-ran,et al. Deep Learning and Recognition of Handwritten Numeral Features[J].,2016,26(12):19.
[12]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(12):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[13]贾翻连,张丽红.基于改进的卷积神经网络的人群密度估计[J].计算机技术与发展,2019,29(02):77.[doi:10．3969/j．issn．1673－629X．2019．02．016]
　JIA Fanlian,ZHANG Lihong.Crowd Density Estimation Based on an Improved Convolution Neural Network[J].,2019,29(12):77.[doi:10．3969/j．issn．1673－629X．2019．02．016]
[14]丁洪金,宫法明.基于时序分析的人体活动状态识别与定位[J].计算机技术与发展,2019,29(04):82.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 017]
　DING Hong-jin,GONG Fa-ming.Human Activities Recognition and Location Based on Temporal Analysis[J].,2019,29(12):82.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 017]
[15]李晓峰,李 东.基于深度学习的高维稀疏数据组合推荐算法[J].计算机技术与发展,2020,30(02):104.[doi:10. 3969 / j. issn. 1673-629X. 2020. 02. 021]
　LI Xiao-feng,LI Dong.A High-dimensional Sparse Data Combination Recommendation Algorithm Based on Deep Learning[J].,2020,30(12):104.[doi:10. 3969 / j. issn. 1673-629X. 2020. 02. 021]
[16]梁 潇,吴 昊,刘全中 *.基于深度学习的多肽预测方法研究[J].计算机技术与发展,2021,31(07):140.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 023]
　LIANG Xiao,WU Hao,LIU Quan-zhong *.Deep PEPred:A Deep Learning-based Approach for Predicting Peptides[J].,2021,31(12):140.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 023]
[17]钟世钦.基于卷积神经网络的网贷违约风险模型研究[J].计算机技术与发展,2022,32(05):123.[doi:10. 3969 / j. issn. 1673-629X. 2022. 05. 021]
　ZHONG Shi-qin.Research on Prediction Model of Internet Loan Default Based on CNN[J].,2022,32(12):123.[doi:10. 3969 / j. issn. 1673-629X. 2022. 05. 021]
[18]王浩畅,孙铭泽.基于 ERNIE-RCNN 模型的中文短文本分类[J].计算机技术与发展,2022,32(06):28.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 005]
　WANG Hao-chang,SUN Ming-ze.Chinese Short Text Classification Based on ERNIE-RCNN Model[J].,2022,32(12):28.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 005]
[19]金海燕,肖照林,蔡 磊,等.显著性目标检测理论与应用研究综述[J].计算机技术与发展,2022,32(09):1.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 001]
　JIN Hai-yan,XIAO Zhao-lin,CAI Lei,et al.Review on Theory and Application of Saliency Target Detection[J].,2022,32(12):1.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 001]
[20]黄 丽,刘心维,肖 建*.基于深度学习的高精度点云补全算法[J].计算机技术与发展,2023,33(04):62.[doi:10. 3969 / j. issn. 1673-629X. 2023. 04. 009]
　HUANG Li,LIU Xin-wei,XIAO Jian*.High Precision Point Cloud Completion Algorithm Based on Deep Learning[J].,2023,33(12):62.[doi:10. 3969 / j. issn. 1673-629X. 2023. 04. 009]

更新日期/Last Update: 2019-12-10