Abstract
As a typical low-resource language pair, besides severely limited by the scale of parallel corpus, Chinese-Lao language pair also has considerable linguistic differences, resulting in poor performance of Chinese-Lao neural machine translation (NMT) task. However, compared with the Chinese-Lao language pair, there are considerable cross-lingual similarities between Thai-Lao languages. According to these features, we propose a novel NMT approach. We first train Chinese-Thai and Thai-Lao NMT models wherein Thai is treated as pivot language. Then the transfer learning strategy is used to extract the encoder and decoder respectively from the two trained models. Finally, the encoder and decoder are combined into a new model and then fine-tuned based on a small-scale Chinese-Lao parallel corpus. We argue that the pivot language Thai can deliver more information to Lao decoder via linguistic similarity and help improve the translation quality of the proposed transfer-based approach. Experimental results demonstrate that our approach achieves 9.12 BLEU on Chinese-Lao translation task using a small parallel corpus, compared to the 7.37 BLEU of state-of-the-art Transformer baseline system using back-translation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Srithirath, A., Seresangtakul, P.: A hybrid approach to lao word segmentation using longest syllable level matching with named entities recognition. In: The 10th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), Krabi, Thailand, pp. 1–5, 15–17 May 2013
Yang, M., Zhou, L., Yu, Z., Gao, S., Guo, J.: Lao named entity recognition based on conditional random fields with simple heuristic information. In: The 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), Zhangjiajie, pp. 1426–1431 (2015)
Zoph, B., Yuret, D., May, J., et al.: Transfer learning for low-resource neural machine translation. arXiv preprint arXiv:1604.02201 (2016)
Nguyen, T.Q., Chiang, D.: Transfer learning across low-resource, related languages for neural machine translation. arXiv preprint arXiv:1708.09803 (2017)
Lakew, S.M., Erofeeva, A., Negri, M., et al.: Transfer learning in multilingual neural machine translation with dynamic vocabulary. arXiv preprint arXiv:1811.01137 ACM Trans. Graph (2018)
Cheng, Y., Yang, Q., Liu, Y., et al.: Joint training for pivot-based neural machine translation. In: 26th International Joint Conference on Artificial Intelligence, Morgan Kaufmann, San Francisco, pp. 3974–3980 (2017)
Kim, Y., et al.: Pivot-Based Transfer Learning for Neural Machine Translation Between Non-English Languages. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (2019). n. pag. Crossref. Web
Ding, C., Utiyama, M., Sumita, E.: Similar southeast asian languages: corpus-based case study on thai-laotian and Malay-Indonesian. In: Proceedings of the 3rd Workshop on Asian Translation, pp. 149–156, Osaka, Japan, 11–17 December 2016
Singvongsa, K., Seresangtakul, P.: Lao-Thai machine translation using statistical model. In: International Joint Conference on Computer Science & Software Engineering. IEEE (2016)
Och, F.J., Ney, H.: A systematic comparison of various statistical alignment models. Comput. Linguist. 29(1), 19–51 (2003)
Isozaki, H., Sudoh, K., Tsukada, H., Duh, K.: HPSG-based preprocessing for English-to-Japanese translation. ACM Trans. Asian Lang. Inf. Process. 11(3), 1–16 (2012)
Papineni, K., Roukos, S., Ward, T., Zhu, W.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of ACL, pp. 311–318 (2002)
Koehn, P.: Statistical significance tests for machine translation evaluation. Proc. EMNLP 2004, 388–395 (2004)
Vaswani, A., et al.: Attention is all you need. In: Guyon, I., (ed.) Advances in Neural Information Processing Systems, vol. 30, pp. 5998–6008 (2017)
Kingma, D.P., Ba, J.: Adam a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations (2015)
Zhang, J., et al.: THUMT: An Open Source Toolkit for Neural Machine Translation (2017). arXiv:1706.06415
Sennrich, R., Haddow, B., Birch, A.: Improving Neural Machine Translation Models with Monolingual Data (2015)
Acknowledgements
We would like to thank the anonymous reviewers for their constructive comments. The work is supported by National Natural Science Foundation of China (Grant Nos. 61732005, 61672271, 61761026, 61762056 and 61866020), National key research and development plan project (Grant No. 2019QY1800), Yunnan high-tech industry development project (Grant No. 201606), and Natural Science Foundation of Yunnan Province (Grant No. 2018FB104).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yu, Z., Yu, Z., Huang, Y., Guo, J., Wang, Z., Man, Z. (2020). Transfer Learning for Chinese-Lao Neural Machine Translation with Linguistic Similarity. In: Li, J., Way, A. (eds) Machine Translation. CCMT 2020. Communications in Computer and Information Science, vol 1328. Springer, Singapore. https://doi.org/10.1007/978-981-33-6162-1_1
Download citation
DOI: https://doi.org/10.1007/978-981-33-6162-1_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-6161-4
Online ISBN: 978-981-33-6162-1
eBook Packages: Computer ScienceComputer Science (R0)