Abstract
Quality Estimation is a task to predict the quality of translations without relying on any references. QE systems are based on neural features but suffer from the limited size of QE data. The best models nowadays transfer bilingual knowledge from parallel data to QE tasks. However, the distribution between parallel data and QE data may lead to the value of parallel data not being used for best. More specifically, there are no errors in parallel translations while there may be more than one error in the translations of QE data. To alleviate this problem, we propose a model that will mask some tokens at the target side on parallel data but still need to predict every target token. And based on this model, we propose a variant model that uses a masked language model at the target side to obtain deep bi-directional information. Besides, we also try different ensemble methods to get better performance of the CCMT20 Quality Estimation Task. Our system finally won second place in the ZH-EN language pair and third place in the EN-ZH language pair.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chen, Z., Tan, Y., Zhang, C., Xiang, Q., Wang, M.: Improving machine translation quality estimation with neural network features. In: Proceedings of the Second Conference on Machine Translation (2017)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2018)
Fan, K., Wang, J., Li, B., Zhou, F., Chen, B., Si, L.: “bilingual expert” can find translation errors. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)
Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Networks (2005)
Kepler, F., Trńous, J., Treviso, M., Vera, M., Martins, A.F.T.: Openkiwi: an open source framework for quality estimation (2019)
Kim, H., Lee, J.H., Na, S.H.: Predictor-estimator using multilevel task learning with stack propagation for neural quality estimation. In: Proceedings of the Second Conference on Machine Translation (2017)
Kozlova, A., Shmatova, M., Frolov, A.: YSDA participation in the wmt’16 quality estimation shared task. In: Proceedings of the First Conference on Machine Translation (2016)
Kreutzer, J., Schamoni, S., Riezler, S.: QUality estimation from ScraTCH (QUETCH): deep learning for word-level translation quality estimation. In: Proceedings of the Tenth Workshop on Statistical Machine Translation, September 2015
Martins, A.F.T., Astudillo, R., Hokamp, C., Kepler, F.: Unbabel’s participation in the WMT16 word-level translation quality estimation shared task. In: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers (2016)
Martins, A., Junczys-Dowmunt, M., Kepler, F., Astudillo, R., Hokamp, C., Grundkiewicz, R.: Pushing the limits of translation quality estimation. Transactions of the Association for Computational Linguistics (2017)
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 (2015)
Shah, K., Bougares, F., Barrault, L., Specia, L.: Shef-lium-nn: sentence level quality estimation with neural network features. In: Proceedings of the First Conference on Machine Translation (2016)
Snover, M., Dorr, B., Schwartz, R., Micciulla, L., Makhoul, J.: A study of translation edit rate with targeted human annotation. In: Proceedings of Association for Machine Translation in the Americas (2006)
Vaswani, A., et al.: Attention is all you need. Advances in Neural Information Processing Systems 30 (2017)
Acknowledgement
The authors would like to thank Yiming Yan for the feedback.
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
Cui, Q., Geng, X., Huang, S., Chen, J. (2020). NJUNLP’s Submission for CCMT20 Quality Estimation Task. 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_11
Download citation
DOI: https://doi.org/10.1007/978-981-33-6162-1_11
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)