Abstract：The machine translation based on recurrent neural network is gradually replacing the statistical machine translation, especially between the major languages in the world. I Due to the shortage of Mongolian corpus, a method of Mongolian-Chinese machine translation based on Convolutional Neural Network is proposed. In the process of encoding the source corpus, through the pooling layer, the semantic relation and information of CNN in the sentence can be obtained according to the characteristics of Mongolian word formation. The experimental result shows that the method outperforms RNN NMT in the aspect of the quality and training speed of the translation.
[1] 苗洪霞,蔡东风,宋彦.基于短语的统计机器翻译方法[J].沈阳航空航天大学学报, 2007, 24(2): 32-34. [2] 戴维·诺克, 彼得·J.伯克. 对数线性模型[M].上海: 格致出版社,2012: 17-29. [3] Cho K, VanMerrienboer B, Gulcehre C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[J]. Computer Science, 2014, 2(11): 23-37. [4] Mikolov T, Karafiát M, Burget L, et al. Recurrent neural network based language model[C]//Proceedings of Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, September. DBLP, 2010: 1045-1048. [5] Prokhorov D V, Si J,Barto A, et al. BPTT and DAC: A common framework for comparison[M]. Handbook of Learning and Approximate Dynamic Programming. John Wiley & Sons, Inc, 2012: 381-404. [6] Jean S, Cho K,Memisevic R, et al. On using very large target vocabulary for neural machine translation[J]. Computer Science, 2014: 11(6): 7-16. [7] Kalchbrenner N,Blunsom P. Recurrent continuous translation models[C]//Proceedings of Association for Computation Linguistics. 2013: 1700-1709. [8] 刘宇鹏, 马春光, 张亚楠. 深度递归的层次化机器翻译模型[J].计算机学报, 2017, 40(4): 861-871. [9] 史晓东, 陈毅东.基于语篇的机器翻译前瞻[C]. 曹右琦,孙茂松.中国中文信息学会二十五周年学术会议.北京: 清华大学出版社,2006: 56-68. [10] 宁静. 基于树到串的蒙汉统计机器翻译研究[D]. 呼和浩特: 内蒙古师范大学硕士学位论文, 2016. [11] 陈炜. 基于神经网络的机器翻译技术研究[D]. 北京: 中国科学院大学硕士学位论文,2016. [12] Meng F, Lu Z, Wang M, et al. Encoding source language with convolutional neural network for machine translation[J]. Computer Science, 2015,11(2): 15-22. [13] Gehring J, Auli M, Grangier D, et al. A Convolutional Encoder Model for Neural Machine Translation[J]. Computation and Language. 2016,8(6): 33-45. [14] 陈先昌. 基于卷积神经网络的深度学习算法与应用研究[D].杭州: 浙江工商大学硕士学位论文,2013. [15] 王龙, 杨俊安, 刘辉,等. 基于RNN汉语语言模型自适应算法研究[J]. 火力与指挥控制, 2016, 41(5): 31-34. [16] 汪宝彬, 汪玉霞. 随机梯度下降法的一些性质[J].数学杂志,2011,31(6): 1041-1044.
2018, Vol. 32 
