Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Multilingual natural language processing

Towards universal translation

State of the art neural network approaches enable massive multilingual translation. How close are we to universal translation between any spoken, written or signed language?

This is a preview of subscription content

Access options

Rent or Buy article

Get time limited or full article access on ReadCube.

from$8.99

All prices are NET prices.

Fig. 1: Pairwise system (left) versus shared system (right).

References

  1. 1.

    Hassan, H. et al. Preprint at https://arxiv.org/abs/1803.05567 (2018).

  2. 2.

    Johnson, M. et al. Trans. Assoc. Comput. Linguist. 5, 339–351 (2017).

    Article  Google Scholar 

  3. 3.

    Tang, Y. et al. Preprint at https://arxiv.org/abs/2008.00401 (2020).

  4. 4.

    Fan, A. et al. Preprint at https://arxiv.org/abs/2010.11125 (2020).

  5. 5.

    Lewis, M. et al. in Proc. 58th Annual Meeting of the Association for Computational Linguistics 7871–7880 (ACL, 2020).

  6. 6.

    Escolano, C., Costa-jussà, M. R., Fonollosa, J. A. R. & Segura, C. Preprint at https://arxiv.org/abs/2011.01097 (2021).

  7. 7.

    Cho, K. et al. in Proc. 2014 Conf. Empirical Methods in Natural Language Processing 1724–1734 (ACL, 2014).

  8. 8.

    Firat, O., Cho, K. & Bengio, Y. in Proc. 2016 Conf. North American Chapter of the Association for Computational Linguistics: Human Language Technologies 866–875 (ACL, 2016).

  9. 9.

    Aharoni, R., Johnson, M. & Firat, O. in Proc. 2019 Conf. North American Chapter of the Association for Computational Linguistics: Human Language Technologies 3874–3884 (ACL, 2019).

  10. 10.

    Vaswani, A. et al. in Proc. 31st Int. Conf. Neural Information Processing Systems 6000–6010 (Curran Associates, 2017).

  11. 11.

    Barrault, L. et al. in Proc. Third Conf. Machine Translation: Shared Task Papers 304–323 (ACL, 2018).

  12. 12.

    Jia, Y. et al. in Proc. INTERSPEECH 1123–1127 (ICSA, 2019).

  13. 13.

    Zhou, S., Zeng, X., Zhou, Y., Anastasopoulos, A. & Neubig, G. in Proc. Fourth Conf. Machine Translation 565–571 (ACL, 2019).

  14. 14.

    Costa-jussà, M. R. Nat. Mach. Intell. 1, 495–496 (2019).

    Article  Google Scholar 

  15. 15.

    Blodgett, S., Barocas, S., Daumé, H. III & Wallach, H. in Proc. 58th Annual Meeting of the Association for Computational Linguistics 5454–5476 (ACL, 2020).

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Marta R. Costa-jussà.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Costa-jussà, M.R. Towards universal translation. Nat Mach Intell 3, 376–377 (2021). https://doi.org/10.1038/s42256-021-00346-7

Download citation

Search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing