Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
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.

  • NEWS AND VIEWS

Meta’s AI translation model embraces overlooked languages

More than 7,000 languages are in use throughout the world, but popular translation tools cannot deal with most of them. A translation model that was tested on under-represented languages takes a key step towards a solution.
  1. David I. Adelani

    1. David I. Adelani is in the Department of Computer Science, University College London Centre for Artificial intelligence, London WC1V 6BH, UK; in the School of Computer Science, McGill University, Montreal, Quebec, Canada, and at Mila — Quebec AI Institute, Montreal, Quebec, Canada.

    View author publications

    You can also search for this author in PubMed  Google Scholar

Machine-translation models use artificial intelligence (AI) to translate one human language into another — a worthy feat, given the potential for enhanced communication to break down the barriers posed by differences in language and culture. Yet most of these models can interpret only a small fraction of the world’s languages, in part because training them requires online data that don’t exist for many languages. The US technology company Meta has designed a project called No Language Left Behind (NLLB) to change that. Writing in Nature, the NLLB team1 presents a publicly available model that can translate between 204 languages, many of which are used in low- and middle-income countries.

Access options

Rent or buy this article

Prices vary by article type

from$1.95

to$39.95

Learn more

Prices may be subject to local taxes which are calculated during checkout

Nature 630, 821-822 (2024)

doi: https://doi.org/10.1038/d41586-024-00964-2

References

  1. NLLB Team. Nature 630, 841–846 (2024).

    Article  Google Scholar 

  2. Bahdanau, D., Cho, K. & Bengio, Y. Preprint at arXiv https://doi.org/10.48550/arXiv.1409.0473 (2014).

  3. Sennrich, R., Haddow, B. & Birch, A. Proc. 54th Annu. Meet. Assoc. Comput. Linguist. (Vol. 1: Long Papers), 1715–1725 (2016).

    Article  Google Scholar 

  4. Vaswani, A. et al. Adv. Neural Inf. Process. Syst. 30, 6000–6010 (2017).

    Google Scholar 

  5. Conneau, A. et al. Proc. 58th Annu. Meet. Assoc. Comput. Linguist. 8440–8451 (2020).

    Article  Google Scholar 

  6. Goyal, N. et al. Trans. Assoc. Comput. Linguist. 10, 522–538 (2022).

    Article  Google Scholar 

  7. Adelani, D. I. et al. Preprint at arXiv https://doi.org/10.48550/arXiv.2309.07445 (2024).

  8. Robinson, N., Ogayo, P., Mortensen, D. R. & Neubig, G. Proc. Eighth Conf. Mach. Transl. 392–418 (2023).

    Article  Google Scholar 

  9. Bandarkar, L. et al. Preprint at arXiv https://doi.org/10.48550/arXiv.2308.16884 (2023).

  10. Adelani, D. et al. Proc. 2022 Conf. North Am. Chapter Assoc. Comput. Linguist. Hum. Lang. Technol. 3053–3070 (2022).

    Article  Google Scholar 

  11. Maillard, J. et al. Proc. 61st Annu. Meet. Assoc. Comput. Linguist. (Vol. 1: Long Papers) 2740–2756 (2023).

    Article  Google Scholar 

  12. Reid, M. et al. Preprint at arXiv https://doi.org/10.48550/arXiv.2403.05530 (2024).

  13. Zhang, K. et al. Preprint at arXiv https://doi.org/10.48550/arXiv.2402.18025 (2024).

Download references

Competing Interests

The author declares no competing interests.

Subjects

Latest on:

Nature Careers

Jobs

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

Search

Advanced search

Quick links