首页 | 官方网站   微博 | 高级检索  
     

面向自然语言处理的深度学习研究
引用本文: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):1445-1465.
作者姓名:奚雪峰  周国栋
作者单位:1.苏州大学计算机科学与技术学院 苏州 215006
基金项目:国家自然科学基金(61331011,61472264)资助
摘    要:近年来,深度学习在图像和语音处理领域已经取得显著进展,但是在同属人类认知范畴的自然语言处理任务中,研究还未取得重大突破.本文首先从深度学习的应用动机、首要任务及基本框架等角度介绍了深度学习的基本概念;其次,围绕数据表示和学习模型两方面,重点分析讨论了当前面向自然语言处理的深度学习研究进展及其应用策略;并进一步介绍了已有的深度学习平台和工具;最后,对深度学习在自然语言处理领域的发展趋势和有待深入研究的难点进行了展望.

关 键 词:自然语言处理    深度学习    表示学习    特征学习    神经网络
收稿时间:2015-11-02

A Survey on Deep Learning for Natural Language Processing
XI Xue-Feng,ZHOU Guo-Dong.A Survey on Deep Learning for Natural Language Processing[J].Acta Automatica Sinica,2016,42(10):1445-1465.
Authors:XI Xue-Feng  ZHOU Guo-Dong
Affiliation:1.School of Computer Science and Technology, Soochow University, Suzhou 2150062.School of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou 2150093.Suzhou Key Laboratory of Mobile Networking and Applied Technologies, Suzhou 215009
Abstract:Recently, deep learning has made significant development in the fields of image and voice processing. However, there is no major breakthrough in natural language processing task which belongs to the same category of human cognition. In this paper, firstly the basic concepts of deep learning are introduced, such as application motivation, primary task and basic framework. Secondly, in terms of both data representation and learning model, this paper focuses on the current research progress and application strategies of deep learning for natural language processing, and further describes the current deep learning platforms and tools. Finally, the future development difficulties and suggestions for possible extensions are also discussed.
Keywords:Natural language processing  deep learning  representation learning  feature learning  neural network
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号