Abstract
In this paper, we describe our submitted system for CCMT 2020 sentence-level quality estimation subtasks and machine translation subtasks. We propose two models: (i) a Transformer-based unified neural network for the quality estimation of machine translation, which consists of a Transformer bottleneck layer and a bidirectional long short-term memory network that are jointly optimized and fine-tuned for quality estimation, and (ii) a Transformer-based re-decoding model for machine translation, which takes the generated machine translation outputs as the approximate contextual environment of the target language and synchronously re-decodes each token in the machine translation outputs. Experimental results on the development set show that the proposed approaches outperform the baseline systems.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Chen, Z., et al.: Improving machine translation quality estimation with neural network features. In: Proceedings of the WMT, pp. 551–555 (2017)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the NAACL, pp. 4171–4186 (2018)
Guo, X., et al.: Kingsoft’s neural machine translation system for wmt19. In: Proceeding of the ACL, pp. 196–202 (2019)
Li, M., Xiang, Q., Chen, Z., Wang, M.: A unified neural network for quality estimation of machine translation. IEICE Trans. Inf. Syst. 101(9), 2417–2421 (2018)
Ott, M., et al.: Fairseq: a fast, extensible toolkit for sequence modeling. In: Proceedings of the NAACL, pp. 48–53 (2019)
Specia, L., Shah, K., De Souza, J.G., Cohn, T.: Quest-a translation quality estimation framework. In: Proceedings of the ACL, pp. 79–84 (2013)
Sun, M., Jiang, B., Xiong, H., He, Z., Wu, H., Wang, H.: Baidu neural machine translation systems for wmt19. In: Proceeding of the ACL, pp. 374–381 (2019)
Vaswani, A., et al.: Attention is all you need. In: Proceedings of the NIPS, pp. 5998–6008 (2017)
Yu, D., Seltzer, M.L.: Improved bottleneck features using pretrained deep neural networks. In: Proceedings of the INTERSPEECH, pp. 237–240 (2011)
41(12), 100–121 (2018)
34(3), 56–63 (2020)
41(12), 100–121 (2018)
34(3), 56–63 (2020)Acknowledgements
This research has been funded by the Natural Science Foundation of China under Grant No.61662031 and 61462044. The authors would like to extend their sincere thanks to the anonymous reviewers who provided valuable comments.
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
Chen, C., Zong, Q., Luo, Q., Qiu, B., Li, M. (2020). Transformer-Based Unified Neural Network for Quality Estimation and Transformer-Based Re-decoding Model for Machine Translation. 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_6
Download citation
DOI: https://doi.org/10.1007/978-981-33-6162-1_6
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)