Abstract
The problem of rare and unknown words is an important issue in Uyghur-Chinese machine translation, especially using neural machine translation model. We propose a novel way to deal with the rare and unknown words. Based on neural machine translation of using pointers over input sequence, our approach which consists of preprocess and post-process can be used in all neural machine translation model. Pre-process modify the Uyghur-Chinese corpus to extend the ability of pointer network, and the post- process retranslating the raw translation by a phrase-based machine translation model or a wordlist. Experiment show that neural machine translation model used the approach proposed by this paper get a higher BLEU score than the phrase-based model in Uyghur-Chinese MT.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wang, Y., Wong, D.F., Chao, L,S,, et al.: The report of NLP 2 CT for CWMT 2015 evaluation task. In: The China Workshop on Machine Translation (2015)
Xiao, L., Tonghai, J., Xi, Z., et al.: An overview of research on the key technology of Uyghur-Chinese machine translation. Netw. New Media Technol. 5(01), 19–25 (2016)
Chen, K.: Research on the key technology of reordering model in Uyghur-Chinese machine translation. University of Chinese Academy of Sciences (2013)
Kong, J., Yang, Y., Wang, L., et al.: Research in corpus filtering technique for Uyghur Chinese Machine Translation. Appl. Res. Comput. 33 (2016)
Aisha, B., Sun, M.: Uyghur-Chinese statistical machine translation by incorporating morphological information. J. Comput. Inf. Syst. 6, 3137–3145 (2010)
Mi, C., Yang, Y., Zhou, X., et al.: A phrase table filtering model based on binary classification for Uyghur-Chinese machine translation. J. Comput. 9(12), 2780–2786 (2014)
Murat, A., Yusup, A., Abaydulla, Y.: Research and implementation of the Uyghur-Chinese personal name transliteration based on syllabification. In: International Conference on Asian Language Processing, pp. 71–74. IEEE (2013)
Devlin, J., Zbib, R., Huang, Z., et al.: Fast and robust neural network joint models for statistical machine translation. In: Meeting of the Association for Computational Linguistics, pp. 1370–1380 (2014)
Zou, W.Y., Socher, R., Cer, D., et al.: Bilingual word embeddings for phrase-based machine translation. In: Empirical Methods in Natural Language Processing (2013)
Cho, K., Van Merrienboer, B., Gulcehre, C., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Empirical Methods in Natural Language Processing (2014)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. Computer Science (2014)
Yang, Y., Mi, C., Ma, B., Dong, R., Wang, L., Li, X.: Character tagging-based word segmentation for Uyghur. In: Shi, X., Chen, Y. (eds.) CWMT 2014. CCIS, vol. 493, pp. 61–69. Springer, Heidelberg (2014). doi:10.1007/978-3-662-45701-6_6
Gulcehre, C., Ahn, S., Nallapati, R., et al.: Pointing the unknown words. Computer Science (2016)
Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. Computer Science (2015)
Acknowledgements
This work is supported by the Young Creative Sci-Tech Talents Cultivation Project of Xinjiang Uyghur Autonomous Region (2014711006, 2014721032), the Natural Science Foundation of Xinjiang (2015211B034), the Xinjiang Key Laboratory Fund under Grant No. 2015KL031 and the Strategic Priority Research Program of the Chinese Academy of Sciences under Grant No. XDA06030400.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Kong, J., Yang, Y., Zhou, X., Wang, L., Li, X. (2016). Research for Uyghur-Chinese Neural Machine Translation. In: Lin, CY., Xue, N., Zhao, D., Huang, X., Feng, Y. (eds) Natural Language Understanding and Intelligent Applications. ICCPOL NLPCC 2016 2016. Lecture Notes in Computer Science(), vol 10102. Springer, Cham. https://doi.org/10.1007/978-3-319-50496-4_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-50496-4_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-50495-7
Online ISBN: 978-3-319-50496-4
eBook Packages: Computer ScienceComputer Science (R0)