Abstract
This paper presents HW-TSC’s submissions to CCMT 2022 Chinese Minority Language Translation task. We participate in three language directions: Mongolian\(\rightarrow \)Chinese Daily Conversation Translation, Tibetan\(\rightarrow \)Chinese Government Document Translation, and Uighur\(\rightarrow \)Chinese News Translation. We train our models using the Deep Transformer architecture, and adopt enhancement strategies such as Regularized Dropout, Tagged Back-Translation, Alternated Training, and Ensemble. Our enhancement experiments have proved the effectiveness of above-mentioned strategies. We submit enhanced systems as primary systems for the three tracks. In addition, we train contrast models using additional bilingual data and submit results generated by these contrast models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1715–1725 (2016)
Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Wang, Q., Li, B., Xiao, T., et al.: Learning deep transformer models for machine translation. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 1810–1822 (2019)
Hinton, G.E., NitishSrivastava, A.K., Salakhutdinov, I.S.R.R.: Improving neural networks by preventing co-adaptation of feature detectors
Wu, L., Li, J., Wang, Y., et al.: R-drop: regularized dropout for neural networks. In: Advances in Neural Information Processing Systems (2021)
Burlot, F., Yvon, F.: Using monolingual data in neural machine translation: a systematic study. In: Proceedings of the Third Conference on Machine Translation: Research Papers, 144–155 (2018)
Edunov, S., Ott, M., Auli, M., et al.: Understanding back-translation at scale. Proc. Conf. Empirical Meth. Nat. Lang. Process. 2018, 489–500 (2018)
Graça, M., Kim, Y., Schamper, J., et al.: Generalizing Back-Translation in Neural Machine Translation. In: Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers), pp. 45–52 (2019)
Caswell, I., Chelba, C., Grangier, D.: Tagged Back-Translation. In: Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers), pp. 53–63 (2019)
Abdulmumin, I., Galadanci, B.S., Isa, A.: Enhanced back-translation for low resource neural machine translation using self-training. In: ICTA 2020. CCIS, vol. 1350, pp. 355–371. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-69143-1_28
Jiao, R., Yang, Z., Sun, M., et al.: Alternated training with synthetic and authentic data for neural machine translation. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 1828–1834 (2021)
Garmash, E., Monz, C.: Ensemble learning for multi-source neural machine translation. In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pp. 1409–1418 (2016)
Yang, H., Wu, Z., Yu, Z., et al.: HW-TSC’s submissions to the WMT21 biomedical translation task. In: Proceedings of the Sixth Conference on Machine Translation, pp. 879–884 (2021)
Ott, M., Edunov, S., Baevski, A., et al.: fairseq: a fast, extensible toolkit for sequence modeling. Proc. Conf. North Am. Chapter Assoc. Comput. Linguist. (Demonstrations) 2019, 48–53 (2019)
Szegedy, C., Vanhoucke, V., Ioffe, S., et al.: Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826. IEEE (2016)
Kingma, D.P, Ba, J.L.: Adam: a method for stochastic optimization (2015)
Junczys-Dowmunt, M., Grundkiewicz, R., Dwojak, T., et al.: Marian: fast neural machine translation in c++. In: ACL 2018–56th Annual Meeting of the Association for Computational Linguistics, Proceedings of System Demonstrations (2015)
Post, M.A.: Call for clarity in reporting BLEU scores. In: Proceedings of the Third Conference on Machine Translation: Research Papers, pp. 186–191 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wu, Z. et al. (2022). Multi-strategy Enhanced Neural Machine Translation for Chinese Minority Languages. In: Xiao, T., Pino, J. (eds) Machine Translation. CCMT 2022. Communications in Computer and Information Science, vol 1671. Springer, Singapore. https://doi.org/10.1007/978-981-19-7960-6_4
Download citation
DOI: https://doi.org/10.1007/978-981-19-7960-6_4
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-7959-0
Online ISBN: 978-981-19-7960-6
eBook Packages: Computer ScienceComputer Science (R0)