Abstract
Machine translation Quality Estimation (QE) aims to estimate the quality of machine translations without relying on golden references. Current QE researches mainly focus on sentence-level QE models, which could not capture discourse-related translation errors. To tackle this problem, this paper presents a novel document-level QE model based on Centering Theory (CT), which is a linguistics theory for assessing discourse coherence. Furthermore, we construct and release an open-source Chinese-English corpus at https://github.com/ydc/cpqe for document-level machine translation QE, which could be used to support further studies. Finally, experimental results show that the proposed model significantly outperformed the baseline model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Banerjee, S., Lavie, A.: Meteor: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, pp. 65–72 (2005)
Chen, Z., et al.: Improving machine translation quality estimation with neural network features. In: Proceedings of the Second Conference on Machine Translation, pp. 551–555 (2017)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Doddington, G.: Automatic evaluation of machine translation quality using n-gram co-occurrence statistics. In: Proceedings of the Second International Conference on Human Language Technology Research, pp. 138–145 (2002)
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, vol. 33, pp. 6367–6374 (2019)
Felice, M., Specia, L.: Linguistic features for quality estimation. In: Proceedings of the Seventh Workshop on Statistical Machine Translation, pp. 96–103 (2012)
Fonseca, E., Yankovskaya, L., Martins, A.F., Fishel, M., Federmann, C.: Findings of the WMT 2019 shared tasks on quality estimation. In: Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2), pp. 1–10 (2019)
Grosz, B., Joshi, A., Weinstein, S.: Providing a unified account of definite noun phrases in discourse. In: Proceedings of the 21st Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics (1983)
Grosz, B.J., Joshi, A.K., Weinstein, S.: Centering: a framework for modelling the local coherence of discourse (1995)
Kim, H., Jung, H.Y., Kwon, H., Lee, J.H., Na, S.H.: Predictor-estimator: Neural quality estimation based on target word prediction for machine translation. ACM Trans. Asian Low-Resour. Lang. Inf. Process. (TALLIP) 17(1), 1–22 (2017)
Kim, H., Lim, J.H., Kim, H.K., Na, S.H.: QE BERT: bilingual BERT using multi-task learning for neural quality estimation. In: Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2), pp. 85–89 (2019)
Lafferty, J., McCallum, A., Pereira, F.C.: Conditional random fields: probabilistic models for segmenting and labeling sequence data (2001)
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)
Martins, A.F., Junczys-Dowmunt, M., Kepler, F.N., Astudillo, R., Hokamp, C., Grundkiewicz, R.: Pushing the limits of translation quality estimation. Trans. Assoc. Computat. Linguist. 5, 205–218 (2017)
Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311–318 (2002)
Patel, R.N., et al.: Translation quality estimation using recurrent neural network. arXiv preprint arXiv:1610.04841 (2016)
Rubino, R., de Souza, J., Foster, J., Specia, L.: Topic models for translation quality estimation for gisting purposes (2013)
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, Cambridge, MA, vol. 200 (2006)
Specia, L., Paetzold, G., Scarton, C.: Multi-level translation quality prediction with quest++. In: Proceedings of ACL-IJCNLP 2015 System Demonstrations, pp. 115–120 (2015)
Tan, Z., et al.: THUMT: an open-source toolkit for neural machine translation. In: Proceedings of the 14th Conference of the Association for Machine Translation in the Americas (AMTA 2020), pp. 116–122 (2020)
Tong, Y., Zheng, J., Zhu, H., Chen, Y., Shi, X.: A document-level neural machine translation model with dynamic caching guided by theme-rheme information. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 4385–4395 (2020)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Voita, E., Sennrich, R., Titov, I.: When a good translation is wrong in context: context-aware machine translation improves on deixis, ellipsis, and lexical cohesion. arXiv preprint arXiv:1905.05979 (2019)
Walker, M.A., Joshi, A.K., Prince, E.F.: Centering in naturally-occurring discourse: an overview. In: Centering in Discourse. Citeseer (1998)
Yang, S., Wang, Y., Chu, X.: A survey of deep learning techniques for neural machine translation. arXiv preprint arXiv:2002.07526 (2020)
Yuan, Y., Sharoff, S.: Sentence level human translation quality estimation with attention-based neural networks. arXiv preprint arXiv:2003.06381 (2020)
Acknowledgements
The authors would like to thank the three anonymous reviewers for their comments on this paper. This research was supported in part by the National Natural Science Foundation of China under Grant Nos. 62076211, U1908216 and 61573294 and the Outstanding Achievement Late Fund of the State Language Commission of China under Grant WT135-38.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendices
A Appendix
The input of the outer-extractor is translation sentences mt, the preferred centers of translation sentences mCp, source sentences src and the preferred centers of source sentences sCp. The output of the extractor are embeddings of preferred centers Emb and the sentence relation features \(f_{outer}\). T is the number of sentences in the corpus.
B Appendix
For preferred center extraction model, we use BERT-Base-Chinese as Chinese pre-trained model and BERT-Base as English pre-trained model. Some hyper-parameters are fixed: decoder layers are 12, hidden size of Bert is 768, the number of heads in multi-head attention is 12. Other parameters are shown in Table 5.
C Appendix
Our CpQE model integrate an outer-extractor compared with baseline model. Other parameters is same as the baseline model. The parameters of baseline is shown in Table 6 and Table 7. The dimension of Word2Vec in outer-extractor is 512.
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, Y., Zhong, E., Tong, Y., Qiu, Y., Shi, X. (2021). A Document-Level Machine Translation Quality Estimation Model Based on Centering Theory. In: Su, J., Sennrich, R. (eds) Machine Translation. CCMT 2021. Communications in Computer and Information Science, vol 1464. Springer, Singapore. https://doi.org/10.1007/978-981-16-7512-6_1
Download citation
DOI: https://doi.org/10.1007/978-981-16-7512-6_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7511-9
Online ISBN: 978-981-16-7512-6
eBook Packages: Computer ScienceComputer Science (R0)