Skip to main content
Springer Nature Link
Log in

Tencent Minority-Mandarin Translation System

  • Conference paper
  • First Online:
Machine Translation (CCMT 2019)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1104))

Included in the following conference series:

  • 466 Accesses

Abstract

This paper describes the submissions of the Tencent minority-mandarin translation system for CCMT19. We participate in 3 translation directions including Uighur\(\rightarrow \)Chinese, Tibetan\(\rightarrow \)Chinese and Mongolian\(\rightarrow \)Chinese. Our systems are neural machine translation systems trained with our improved Marian, and are called TenTrans, which are based on Google’s Transformer model architecture. We also adopt most techniques that have been proven effective recently in academia, such as back-translation based sampling, data selection, sequence-level knowledge distillation, ensemble distillation, model ensembling and reranking. By using the above technologies, our submitted systems achieve a stable performance improvement.

B. Hu, A. Han, Z. Zhang—Equal contribution.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    https://github.com/marian-nmt/marian.

  2. 2.

    https://github.com/tensorflow/tensor2tensor.

  3. 3.

    https://github.com/pytorch/fairseq.

  4. 4.

    This setting is slightly different from big model in tensor2tensor and Fairseq, which is the best parameter setting we have ever tried.

  5. 5.

    https://code.google.com/archive/p/word2vec/.

  6. 6.

    https://github.com/clab/fast_align.

  7. 7.

    XMU corpus: http://nlp.nju.edu.cn/cwmt2018/resources.html.

  8. 8.

    The used BERT is developed by our department’s NLP team.

  9. 9.

    https://github.com/kpu/kenlm.

  10. 10.

    http://www.xunsearch.com/scws/.

  11. 11.

    Using official scoring programs and requirements.

References

  1. Cho, K., Merrienboer, B., Gulcehre, C., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: EMNLP (2014)

    Google Scholar 

  2. Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104–3112 (2014)

    Google Scholar 

  3. Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of ICLR (2014)

    Google Scholar 

  4. Sennrich, R., Haddow, B., Birch, A.: Edinburgh neural machine translation systems for WMT 2016. In: Proceedings of the First Conference on Machine Translation. Association for Computational Linguistics, Berlin, Germany (2016)

    Google Scholar 

  5. Wu, Y., et al.: Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. CoRR, abs/1609.08144 (2016)

    Google Scholar 

  6. Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)

    Google Scholar 

  7. Junczys-Dowmunt, M., et al.: Marian: fast neural machine translation in C++. In: Proceedings of ACL: System Demonstrations, p. 2018. Association for Computational Linguistics, Melbourne, Australia (2018)

    Google Scholar 

  8. Hu, B., Han, A., Huang, S.: TencentFmRD neural machine translation for WMT 2018. In: Proceedings of the Third Conference on Machine Translation: Shared Task Papers. Association for Computational Linguistics, Belgium, Brussels (2018)

    Google Scholar 

  9. Hu, B., Han, A., Huang, S.: TencentFmRD neural machine translation system. In: Chen, J., Zhang, J. (eds.) CWMT 2018. CCIS, vol. 954, pp. 111–123. Springer, Singapore (2019). https://doi.org/10.1007/978-981-13-3083-4_11

    Chapter  Google Scholar 

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

    Google Scholar 

  11. Luong, M., Manning, C.D.: Achieving open vocabulary neural machine translation with hybrid word-character models. In: Proceedings of ACL (2016)

    Google Scholar 

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

    Google Scholar 

  13. Edunov, S., Ott, M., Auli, M., Grangier, D.: Understanding back-translation at scale. In: Proceedings of the: Conference on Empirical Methods in Natural Language Processing, p. 2018. Association for Computational Linguistics, Brussels, Belgium (2018)

    Google Scholar 

  14. Imamura, K., Fujita, A., Sumita, E.: Enhancement of encoder and attention using target monolingual corpora in neural machine translation. In: Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pp. 55–63 (2018)

    Google Scholar 

  15. Hoang, V.C.D., Koehn, P., Haffari, G., Cohn, T.: Iterative back-translation for neural machine translation. In: Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pp. 18–24 (2018)

    Google Scholar 

  16. Kim, Y., Rush, A.M.: Sequence-level knowledge distillation. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 1317–1327. Association for Computational Linguistics, Austin, Texas (2016)

    Google Scholar 

  17. Freitag, M., Al-Onaizan, Y., Sankaran, B.: Ensemble distillation for neural machine translation. arXiv preprint arXiv:1702.01802 (2017)

  18. Denkowski, M., Neubig, G.: Stronger baselines for trustable results in neural machine translation. In: Proceedings of the First Workshop on Neural Machine Translation, pp. 18–27 (2017)

    Google Scholar 

  19. Sennrich, R., et al.: The University of Edinburgh neural MT systems for WMT 2017. In: Proceedings of the Second Conference on Machine Translation, pp. 389–399 (2017)

    Google Scholar 

  20. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)

    MathSciNet  MATH  Google Scholar 

  21. Cherry, C., Foster, G.: Batch tuning strategies for statistical machine translation. In: Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 427–436. Association for Computational Linguistics (2012)

    Google Scholar 

  22. Ott, M., et al.: FAIRSEQ: a fast, extensible toolkit for sequence modeling. In: NAACL HLT 2019 (2019)

    Google Scholar 

  23. Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

  24. Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. In: International Conference on Machine Learning, pp. 1310–1318 (2013)

    Google Scholar 

  25. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)

    Google Scholar 

  26. Ramachandran, P., Zoph, B., Le, Q.V.: Searching for activation functions. arXiv preprint arXiv:1710.05941 (2017)

  27. 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 on Association for Computational Linguistics, pp. 311–318. Association for Computational Linguistics (2002)

    Google Scholar 

  28. Chen, B., Cherry, C., Foster, G., Larkin, S.: Cost weighting for neural machine translation domain adaptation. In: Proceedings of the First Workshop on Neural Machine Translation, pp. 40–46 (2017)

    Google Scholar 

  29. Zhang, S., Xiong, D.: Sentence weighting for neural machine translation domain adaptation. In: Proceedings of the 27th International Conference on Computational Linguistics, pp. 3181–3190 (2018)

    Google Scholar 

  30. Wang, R., Utiyama, M., Liu, L., Chen, K., Sumita, E.: Instance weighting for neural machine translation domain adaptation. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 1482–1488 (2017)

    Google Scholar 

  31. 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)

  32. Chen, W., Matusov, E., Khadivi, S., Peter, J.T.: Guided alignment training for topic-aware neural machine translation. arXiv preprint arXiv:1607.01628 (2016)

  33. Deng, Y., et al.: Alibaba’s neural machine translation systems for WMT 2018. In: Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pp. 368–376 (2018)

    Google Scholar 

  34. Junczys-Dowmunt, M.: Microsoft’s submission to the WMT 2018 news translation task: how i learned to stop worrying and love the data. In: Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pp. 425–430 (2018)

    Google Scholar 

  35. Axelrod, A., He, X., Gao, J.: Domain adaptation via pseudo in-domain data selection. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 355–362. Association for Computational Linguistics (2011)

    Google Scholar 

  36. Chen, B., Huang, F.: Semi-supervised convolutional networks for translation adaptation with tiny amount of in-domain data. In: Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning, pp. 314–323 (2016)

    Google Scholar 

  37. Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)

  38. Luong, M.T., Manning, C.D.: Stanford neural machine translation systems for spoken language domains. In: Proceedings of the International Workshop on Spoken Language Translation, pp. 76–79 (2015)

    Google Scholar 

  39. Liu, L., Utiyama, M., Finch, A., Sumita, E.: Agreement on target-bidirectional neural machine translation. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 411–416 (2016)

    Google Scholar 

  40. Tu, Z., Liu, Y., Shang, L., Liu, X., Li, H.: Neural machine translation with reconstruction. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Tencent Minority-Mandarin Translation, Beijing, China

    Bojie Hu, Ambyer Han, Shen Huang & Qi Ju

  2. Natural Language Processing Lab, Northeastern University, Shenyang, China

    Zheyang Zhang

Authors
  1. Bojie Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ambyer Han
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zheyang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shen Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Qi Ju
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bojie Hu .

Editor information

Editors and Affiliations

  1. Nanjing University, Nanjing, China

    Shujian Huang

  2. Didi Labs, University of Southern California, Marina Del Rey, CA, USA

    Kevin Knight

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Hu, B., Han, A., Zhang, Z., Huang, S., Ju, Q. (2019). Tencent Minority-Mandarin Translation System. 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_10

Download citation

  • DOI: https://doi.org/10.1007/978-981-15-1721-1_10

  • 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)

Publish with us

Policies and ethics