Semantic Integrity Analysis Based on Recurrent Neural Network
CSTR:
Author:
  • Article
  • | |
  • Metrics
  • |
  • Reference [15]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    This study proposes a semantic integrity analysis method based on recurrent neural network. By judging whether the sentence is semantically complete, the long text is divided into multiple semantic complete sentences. First, dividing the sentences into words, mapped to the corresponding word vector and labeled. Then the word vector and the annotation information are processed by the loop window and the undersampling method, and used as the input of the recurrent neural network. Finally we get the model by training. The result of experiment indicates that this method can achieve an accuracy of 91.61%. This method is the basis of automatic assessment of the subjective questions, and also helps the research of semantic analysis, question and answer system and machine translation.

    Reference
    [1] 林奕欧,雷航,李晓瑜,等.自然语言处理中的深度学习:方法及应用.电子科技大学学报, 2017, 46(6):913-919.[doi:10.3969/j.issn.1001-0548.2017.06.021
    [2] Mikolov T, Chen K, Corrado G, et al. Efficient estimation of word representations in vector space. arXiv:1301.3781, 2013.
    [3] Graves A. Generating sequences with recurrent neural networks. arXiv:1308.0850v5, 2013.
    [4] Tang DY, Qin B, Liu T. Document modeling with gated recurrent neural network for sentiment classification. Proceedings of 2015 Conference on Empirical Methods in Natural Language Processing. Lisbon, Portugal, 2015:1422-1432
    [5] 何炎祥,孙松涛,牛菲菲,等.用于微博情感分析的一种情感语义增强的深度学习模型.计算机学报, 2017, 40(4):773-790
    [6] 刁琦,古丽米拉·克孜尔别克,钟丽峰,等.基于循环神经网络序列标注的中文分词研究.计算机技术与发展, 2017, 27(10):65-68.[doi:10.3969/j.issn.1673-629X.2017.10.014
    [7] 李艳翠,冯文贺,周国栋,等.基于逗号的汉语子句识别研究.北京大学学报(自然科学版), 2013, 49(1):7-14
    [8] 王博立,史晓东,苏劲松.一种基于循环神经网络的古文断句方法.北京大学学报(自然科学版), 2017, 53(2):255-261
    [9] Dyer C, Ballesteros M, Ling W, et al. Transition-based dependency parsing with stack long short-term memory. arXiv:1505.08075, 2015.
    [10] 赵楠,张小芳,张利军.不平衡数据分类研究综述.计算机科学, 2018, 45(6A):22-27, 57
    [11] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout:A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 2014, 15(1):1929-1958
    [12] 周志华.机器学习.北京:清华大学出版社, 2016.
    [13] Kingma DP, Ba J. Adam:A method for stochastic optimization. arXiv:1412.6980, 2014.
    [14] Zeiler MD. ADADELTA:An adaptive learning rate method. arXiv:1212.5701, 2012.
    [15] Reddi SJ, Kale S, Kumar S. On the convergence of Adam and beyond. International Conference on Learning Representations. New York, NY, USA. 2018.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

刘京麦野,刘新,郭炳元,孙道秋.基于循环神经网络的语义完整性分析.计算机系统应用,2019,28(9):203-208

Copy
Share
Article Metrics
  • Abstract:1634
  • PDF: 3217
  • HTML: 2749
  • Cited by: 0
History
  • Received:March 11,2019
  • Revised:April 04,2019
  • Online: September 09,2019
  • Published: September 15,2019
Article QR Code
You are the first990354Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-3
Address:4# South Fourth Street, Zhongguancun,Haidian, Beijing,Postal Code:100190
Phone:010-62661041 Fax: Email:csa (a) iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063