Skip to main content
SpringerLink
Log in

Improving the Quality of Machine Translation Using the Reverse Model

  • THEMATIC ISSUE
  • Published:
Automation and Remote Control Aims and scope Submit manuscript

Abstract

Machine translation is a natural language text processing task that aims to automatically translate input text from one language into another language. The currently known machine translation models show a fairly high quality of translation between large languages, but for smaller language areas, represented by less data, the problem is still not solved. Different methods are used to deal with various errors in automatic translation systems. This paper discusses approaches that use translation models of reverse language directions and improve consistency between translations of the same text using direct and reverse translation models. The paper presents a general theoretical justification for such methods in terms of solving the likelihood maximization problem and also proposes a method for stable training of modern models using cyclic translations.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1.

REFERENCES

  1. Stahlberg, F., Neural machine translation: A review, J. Artif. Intell. Res., 2020, no. 69, pp. 343–418.

  2. Yingce Xia, Di He, Tao Qin, et al., Dual learning for machine translation, Proc. 30th Int. Conf. Neural Inf. Process. Syst. (NIPS’16), Red Hook, NY: Curran Assoc., 2016, pp. 820–828.

  3. Bahdanau, D., Cho, K., and Bengio, Y., Neural Machine Translation by Jointly Learning to Align and Translate, CoRR, 2015. arXiv:1409.0473.

  4. Kaplan, J., McCandlish, S., Henighan, T., et al., Scaling Laws for Neural Language Models. https://arxiv.org/abs/.

  5. Vaswani, A., Shazeer, N., Parmar, N., et al., Attention is all you need, Proc. 31st Int. Conf. Neural Inf. Process. Syst. (NIPS’17), Red Hook, NY: Curran Assoc., 2017, pp. 6000–6010.

  6. Kingma, D. and Ba, J., Adam: A method for stochastic optimization, 3rd Int. Conf. Learn. Representations, ICLR 2015. Conf. Track Proc. (San Diego, CA, May 7–9, 2015).

  7. Papineni, K., Roukos, S., Ward, T., et al., Bleu: A method for automatic evaluation of machine translation, Proc. 40th Annu. Meet. Assoc. Comput. Linguist. (2002), pp. 311–318.

  8. Bojar, O., Chatterjee, R., Federmann, C., et al., Findings of the 2017 Conference on Machine Translation (WMT17), Proc. Second Conf. Mach. Transl. (2017), vol. 2 (Shared Task Papers).

  9. Shaw, P., Uszkoreit, J., and Vaswani, A., Self-attention with relative position representations, Proc. 2018 Conf. North Am. Ch. Assoc. Comput. Linguist.: Human Lang. Technol. (2018), vol. 2 (Short Papers), pp. 464–468.

Download references

Author information

Authors and Affiliations

  1. Federal Research Center “Computer Science and Control,” Russian Academy of Sciences, Moscow, 119333, Russia

    N. A. Skachkov & K. V. Vorontsov

Authors
  1. N. A. Skachkov
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. K. V. Vorontsov
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to N. A. Skachkov or K. V. Vorontsov.

Additional information

Translated by V. Potapchouck

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Skachkov, N.A., Vorontsov, K.V. Improving the Quality of Machine Translation Using the Reverse Model. Autom Remote Control 83, 1897–1907 (2022). https://doi.org/10.1134/S00051179220120049

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S00051179220120049

Keywords

Search

Navigation