The Research on Mongolian and Chinese Machine Translation Based on CNN Numerals Analysis

  • Wu NierEmail author
  • Su Yila
  • Wanwan Liu
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 858)


With the progress of science and technology and the development of artificial intelligence, the Machine Translation method based on neural network replaces statistical method better because of its translation, especially in the aspect of inter-translation among the major languages in the world. Recurrent neural network can extract more features when encoding the source language, which is vital to the quality of translation. In the aspect of translating Mongolian, it is difficult to obtain semantic relations sufficiently from the corpus due to lacking corpus. Therefore, a method of Mongolian-Chinese machine translation based on Convolutional Neural Network (CNN) is proposed. Analysis of Mongolian numerals is to improve the encoder and then selection out of vocabulary. In the process of encoding source language, through the pooling layer, the semantic relation and the series of key information of convolution neural network in the sentence can be obtained. Then, through the Gated Recurrent Unit adds to the global attention mechanism, the source language after encoding can be decoded into Chinese. The experimental result shows that the method takes advantage of the recurrent neural network (RNN) in the aspect of the accuracy and training speed of the translation.


Machine translation Mongolian and Chinese CNN Global attention mechanism Numerals 


  1. 1.
    Miao, H., Cai, D., Song, Y.: Phrase-based statistical machine translation. J. Shenyang Inst. Aeronaut. Eng. 24(2), 32–34 (2007)Google Scholar
  2. 2.
    Knoke, D, Burke, P.J.: Log-Linear Model. Truth&Wisdom Press, Shanghai (2012)Google Scholar
  3. 3.
    Cho, K., Van Merrienboer, B., Gulcehre, C., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. Comput. Sci. 2(11), 23–37 (2014)Google Scholar
  4. 4.
    Mikolov, T., Karafiát, M., Burget, L., et al.: Recurrent neural network based language model. In: Conference of the International Speech Communication Association, INTERSPEECH 2010, Makuhari, Chiba, Japan, September. DBLP, pp. 1045–1048 (2010)Google Scholar
  5. 5.
    Prokhorov, D.V., Si, J., Barto, A., et al.: BPTT and DAC—A Common Framework for Comparison. Handbook of Learning and Approximate Dynamic Programming, pp. 381–404. Wiley, Hoboken (2012)Google Scholar
  6. 6.
    Jean, S., Cho, K., Memisevic, R., et al.: On using very large target vocabulary for neural machine translation. Comput. Sci. (2014)Google Scholar
  7. 7.
    Kalchbrenner, N., Blunsom, P.: Recurrent continuous translation models (2013)Google Scholar
  8. 8.
    Liu, Y., Ma, C., Zhang, Y.: Hierarchical machine translation model based on deep recursive neural network. Chin. J. Comput. 40(4), 861–871 (2017)Google Scholar
  9. 9.
    Shi, X., Chen, Y.: Machine translation prospect based on discourse. In: Chinese Information Processing Society of China 25th Anniversary Academic Conference (2006)Google Scholar
  10. 10.
    Chen-wei: The research of Machine Translation technology based on Neural Network. University of Chinese Academy of Sciences (2016)Google Scholar
  11. 11.
    Chen, X.: Research on algorithm and application of deep learning based on convolutional neural network. Zhejiang Gongshang University (2013)Google Scholar
  12. 12.
    Wang, L., Yang, J., Liu, H., et al.: Research on a self-adaption algorithm of recurrent neural network based Chinese language model. Fire Control Command Control 41(5), 31–34 (2016)Google Scholar
  13. 13.
    Wang, B., Wang, Y.: Some properties relating to stochastic gradient descent methods. J. Math. 31(6), 1041–1044 (2011)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.College of Information EngineeringInner Mongolia University of TechnologyHohhotChina

Personalised recommendations