Mongolian-Chinese Neural Machine Translation Based on RNN and CNN
BAO Wugedele1,2, ZHAO Xiaobing2
1.School of Computer, Hohhot Minzu College, Hohhot, Inner Mongolia 010051, China; 2.School of Information Engineering Minzu University of China, Beijing 100081 , China
Abstract：In this paper, Mongolian-Chinese neural machine translation model based on RNN and CNN is discussed. Mongolian word model, segmentation model and subword model are used as input signals of the translation system. We compare our method with the traditional phrase-based SMT. Experimental results show that the subword model can effectively improve the quality of NMT and the RNN-based Mongolian-Chinese NMT model has surpassed the traditional phrase-based SMT model.
[1] 娜步青.基于统计的蒙汉机器翻译系统[D].呼和浩特: 内蒙古大学硕士学位论文,2006. [2] 银花.基于短语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,2011. [3] 苏传捷.基于层次短语模型的蒙-汉统计机器翻译研究[D].呼和浩特: 内蒙古大学硕士学位论文,2014. [4] 玉霞.蒙古语词法分析及其在蒙汉统计机器翻译中的应用[D].呼和浩特: 内蒙古师范大学硕士学位论文,2015. [5] Sutskever I, Vinyals O, Le Q V. Sequence to sequence learning with neural networks[C]//Proceedings of NIPS 2014: 3104-3112. [6] Cho K, Merrienboer B V, Gulcehre C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of EMNLP 2014: 1724-1734. [7] Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate[DB/OL], 2015.https://arxiv.org/pdf/1409.0473.pdf. [8] Gehring J, Auli M, Grangier D, et al. A convolutional encoder model for neural machine translation[C]//Proceedings of ACL 2017: 123-135. [9] Gehring J, Auli M, Grangier D, et al. Convolutional sequence to sequence learning[DB/OL], http://cslt.riit.tsinghua.edu.cn/mediawiki/images/b/bb/Cnn_seq2seq.pdf. [10] Luong M T, Sutskever I, Le Q V, et al. Addressing the rare word problem in neural machine translation[C]//Proceedings of ACL 2015: 11-19. [11] Li X, Zhang J, Zong C. Towards zero unknown word in neural machine translation[C]//Proceedings of IJCAI 2016: 2852-2858. [12] Jean S, Cho K, Memisevic R, et al. On using very large target vocabulary for neural machine translation[C]//Proceedings of ACL 2015: 1-10. [13] Ling W, Trancoso I, Dyer C, et al. Character-based neural machine translation[DB/OL], 2015. http://diyhpl.us/~bryan/papers2/ai/speech-recognition/Character-based neural machine translation-2015.pdf. [14] Costa-Jussà M R, Fonollosa J A R. Character-based neural machine translation[C]//Proceedings of ACL 2016: 357-361. [15] Luong M T, Manning C D. Achieving open vocabulary neural machine translation with hybrid word-character models[C]//Proceedings of ACL 2016: 1054-1063. [16] Sennrich R, Haddow B, Birch A. Neural machine translation of rare words with subword units[C]//Proceedings of ACL 2016: 1715-1725. [17] 李良友,贡正仙,周国栋.机器翻译自动评价综述[J].中文信息学报,2014,28(03): 81-91.
2018, Vol. 32 
