Abstract
The goal of China Conference on Machine Translation (CCMT 2019) Shared Task on Quality Estimation (QE) is to investigate automatic methods for estimating the quality of \( {\text{Chinese}}\!\leftrightarrow\!{\text{English}} \) machine translation results without reference translations. This paper presents the submissions of our team for the sentence-level Quality Estimation shared task of CCMT19. Considering the good performance of neural models in previous shared tasks of WMT, our submissions also include two neural-based models: one is Bi-Transformer which proposes the model as a feature extractor with a bidirectional transformer and then processes the semantic representations of source and the translation output with a Bi-LSTM predictive model for automatic quality estimation, and the other BiRNN architecture uses only two bi-directional RNNs (bi-RNN) with Gated Recurrent Units (GRUs) as encoders, and learns representation of the source and translation sentence pairs to predict the quality of translation outputs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bicici, E.: Referential translation machines for quality estimation. In: Proceedings of the Eighth Workshop on Statistical Machine Translation, Sofia, Bulgaria, pp. 343–351 (2013)
Blatz, J., Fitzgerald, E., Foster, G., et al.: Confidence estimation for machine translation. In: Proceedings of the 20th International Conference on Computational Linguistics, p. 315 (2004)
Cho, K., van Merrienboer, B., Gulcehre, C., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, pp. 1724–1734 (2014)
Fan, K., Li, B., Zhou, F., Wang, J.: “Bilingual expert” can find translation errors. arXiv preprint. arXiv:1807.09433 (2018)
Graves, A., Schmidhuber, J.: Frame-wise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18(5–6), 602–610 (2005)
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, Copenhagen, Denmark, pp. 562–568 (2017)
Martins, A.F.T., Kepler, F., Monteiro, J.: Unbabel’s participation in the WMT17 translation quality estimation shared task. In: Proceedings of the Second Conference on Machine Translation, Copenhagen, Denmark, pp. 569–574 (2017)
Specia, L., Shah, K., Souza, J.G.C., Cohn, T.: QuEst-a translation quality estimation framework. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics: System Demonstrations, Sofia, Bulgaria, pp. 79–84 (2013)
Specia, L., Paetzold, G., Scarton, C.: Multi-level translation quality prediction with QuEst++. In: Proceedings of ACL 2015, Beijing, China, pp. 115–120 (2015)
Ueffing, N., Ney, H.: Word-level confidence estimation for machine translation. Comput. Linguist. 33(1), 9–40 (2007)
Wang, J., Fan, K., Li, B., et al.: Alibaba submission for WMT18 quality estimation task. In: Proceedings of the Third Conference on Machine Translation, Brussels, Belgium, pp. 822–828 (2018)
Vaswani, A.., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Zeiler, M.D.: ADADELTA: an adaptive learning rate method. arXiv:1212.5701 (2012)
Acknowledgment
This work is supported by China Postdoctoral Science Foundation (CPSF, Grant No. 2018M640069).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, Y., Feng, C., Li, H. (2019). Quality Estimation with Transformer and RNN Architectures. In: Huang, S., Knight, K. (eds) Machine Translation. CCMT 2019. Communications in Computer and Information Science, vol 1104. Springer, Singapore. https://doi.org/10.1007/978-981-15-1721-1_7
Download citation
DOI: https://doi.org/10.1007/978-981-15-1721-1_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-1720-4
Online ISBN: 978-981-15-1721-1
eBook Packages: Computer ScienceComputer Science (R0)