Skip to main content

Tsinghua University Neural Machine Translation Systems for CCMT 2020

  • Conference paper
  • First Online:
Machine Translation (CCMT 2020)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1328))

Included in the following conference series:

  • 376 Accesses

Abstract

This paper describes the neural machine translation system of Tsinghua University for the bilingual translation task of CCMT 2020. We participated in the Chinese \(\leftrightarrow \) English translation tasks. Our systems are based on Transformer architectures and we verified that deepening the encoder can achieve better results. All models are trained in a distributed way. We employed several data augmentation methods, including knowledge distillation, back-translation, and domain adaptation, which are all shown to be effective to improve translation quality. Distinguishing original text from translationese can lead to better results when performing domain adaptation. We found model ensemble and transductive ensemble learning can further improve the translation performance over the individual model. In both Chinese \(\rightarrow \) English and English \(\rightarrow \) Chinese translation tasks, our systems achieved the highest case-sensitive BLEU score among all submissions.

G. Chen, S. Wang and X. Huang—Equal contributions. Listing order is random.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    https://github.com/fxsjy/jieba.

  2. 2.

    https://github.com/moses-smt/mosesdecoder.

  3. 3.

    https://github.com/THUNLP-MT/THUMT.

  4. 4.

    https://github.com/rsennrich/subword-nmt.

References

  1. Edunov, S., Ott, M., Auli, M., Grangier, D.: Understanding back-translation at scale. In: Proceedings of EMNLP (2018)

    Google Scholar 

  2. Kim, Y., Rush, A.M.: Sequence-level knowledge distillation. In: Proceedings of EMNLP (2016)

    Google Scholar 

  3. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of ICLR (2015)

    Google Scholar 

  4. Sennrich, R., Haddow, B., Birch, A.: Improving neural machine translation models with monolingual data. In: Proceedings of ACL (2016)

    Google Scholar 

  5. Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Proceedings of ACL (2016)

    Google Scholar 

  6. Sun, M., Jiang, B., Xiong, H., He, Z., Wu, H., Wang, H.: Baidu neural machine translation systems for WMT19. In: Proceedings of the Fourth Conference on Machine Translation (2019)

    Google Scholar 

  7. Vaswani, A., et al.: Attention is all you need. In: Proceedings of NeurIPS (2017)

    Google Scholar 

  8. Wang, Q., et al.: Learning deep transformer models for machine translation. In: Proceedings of ACL (2019)

    Google Scholar 

  9. Wang, Y., Wu, L., Xia, Y., Qin, T., Zhai, C., Liu, T.Y.: Transductive ensemble learning for neural machine translation. In: AAAI (2020)

    Google Scholar 

  10. Wei, H.R., Huang, S., Wang, R., Dai, X., Chen, J.: Online distilling from checkpoints for neural machine translation. In: Proceedings of NAACL-HLT (2019)

    Google Scholar 

Download references

Acknowledgements

This work was supported by the National Key R&D Program of China (No. 2017YFB0 202204), National Natural Science Foundation of China (No. 61925601, No. 61761166 008, No. 61772302), Beijing Academy of Artificial Intelligence, and the NExT++ project supported by the National Research Foundation, Prime Ministers Office, Singapore under its IRC@Singapore Funding Initiative.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Yang Liu .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Chen, G., Wang, S., Huang, X., Tan, Z., Sun, M., Liu, Y. (2020). Tsinghua University Neural Machine Translation Systems for CCMT 2020. 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_9

Download citation

  • DOI: https://doi.org/10.1007/978-981-33-6162-1_9

  • 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)

Publish with us

Policies and ethics