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.

An analysis of gender bias studies in natural language processing

Nature Machine Intelligence volume 1, pages 495–496 (2019)Cite this article

Subjects

Artificial intelligence systems copy and amplify existing societal biases, a problem that by now is widely acknowledged and studied. But is current research of gender bias in natural language processing actually moving towards a resolution, asks Marta R. Costa-jussà.

Demographic biases in artificial intelligence applications are causing alarm both in the scientific community and in the general public. From systems that recognize European or American faces but struggle with Asian ones to those that prioritize less qualified male candidates over more qualified female ones, our automatic tools are just perpetuations of our stereotypes and prejudices. Because gender bias is one of the most prevalent biases in our society, it is relevant to analyse how recent studies are defining an entire new field of research within natural language processing (NLP). The main questions to address are whether these studies propose scalable evaluation procedures and whether they have a well-defined scope, and taken together, whether they are moving in the right direction towards a resolution of the problem.

This is a preview of subscription content, access via your institution

Access options

Rent or buy this article

Get just this article for as long as you need it

$39.95

Learn more

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

References

  1. O’Neil, C. Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy (Crown, 2016).

  2. Calders, T. & Verwer, S. Data Min. Knowl. Discov. 21, 277–292 (2010).

    Article  MathSciNet  Google Scholar 

  3. LeCun, Y., Bengio, Y. & Hinton, G. Nature 521, 436–444 (2015).

    Article  Google Scholar 

  4. Cislak, A., Formanowicz, M. & Saguy, T. Scientometrics 115, 189–200 (2018).

    Article  Google Scholar 

  5. Ross, K., Boyle, K., Carter, C. & Ging, D. Journalism Stud. 19, 824–845 (2018).

    Article  Google Scholar 

  6. Sweeney, L. Queue 11, 29 (2013).

    Article  Google Scholar 

  7. Bolukbasi, T., Chang, K.-W., Zou, J., Saligrama, V. & Kalai, A. In Proc. 30th International Conference on Neural Information Processing Systems 4356–4364 (Curran Associates, 2016).

  8. Caliskan, A., Bryson, J. J. & Narayanan, A. Science 356, 183–186 (2017).

    Article  Google Scholar 

  9. Zhao, J., Zhou, Y., Li, Z., Wang, W. & Chang, K.-W. Proc. 2018 Conference on Empirical Methods in Natural Language Processing 4847–4853 (Association for Computational Linguistics, 2018) (2018).

  10. Nissim, M., van Noord, R. & van der Goot, R. Preprint at http://arxiv.org/abs/1905.09866 (2019).

  11. Gonen, H. & Goldberg, Y. In Proc. 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies 609–614 (Association for Computational Linguistics, 2019).

  12. Basta, C., Costa-jussà, M. R. & Casas, N. In Proc. First Workshop on Gender Bias in Natural Language Processing 33–39 (Association for Computational Linguistics, 2019).

  13. Vanmassenhove, E., Hardmeier, C. & Way, A. In Proc. 2018 Conference on Empirical Methods in Natural Language Processing 3003–3008 (Association for Computational Linguistics, 2018).

  14. Escudé Font, J. & Costa-jussà, M. R. In Proc. First Workshop on Gender Bias in Natural Language Processing 147–154 (Association for Computational Linguistics, 2019).

  15. Stanovsky, G., Smith, N. A. & Zettlemoyer, L. In Proc. 57th Annual Meeting of the Association for Computational Linguistics 1679–1684 (Association for Computational Linguistics, 2019).

  16. Menegatti, M. & Rubini, M. Oxford Research https://doi.org/10.1093/acrefore/9780190228613.013.470 (2017).

  17. Lewis, M. & Lupyan, G. Preprint at https://psyarxiv.com/7qd3g (2019).

  18. Lindqvist, A., Renström, E. A. & Gustafsson Sendén, M. Sex Roles 81, 109–117 (2019).

    Article  Google Scholar 

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

Download references

Acknowledgements

This work is supported by the Spanish Ministry of Economy and Competitiveness and the European Regional Development Fund (MINECO/ERDF, EU) through the programme Ramón y Cajal.

Author information

Authors and Affiliations

  1. Universitat Politècnica de Catalunya, Barcelona, Spain

    Marta R. Costa-jussà

Authors
  1. Marta R. Costa-jussà
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Marta R. Costa-jussà.

Rights and permissions

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Costa-jussà, M.R. An analysis of gender bias studies in natural language processing. Nat Mach Intell 1, 495–496 (2019). https://doi.org/10.1038/s42256-019-0105-5

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42256-019-0105-5

This article is cited by

Search

Advanced 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