Gender Bias in Machine Translation
Open accessThe DOI matches its Crossref record; 50 of the 50 references it cites were found in a registry or an index.
Abstract
Machine translation (MT) technology has facilitated our daily tasks by providing accessible shortcuts for gathering, processing, and communicating information. However, it can suffer from biases that harm users and society at large. As a relatively new field of inquiry, studies of gender bias in MT still lack cohesion. This advocates for a unified framework to ease future research. To this end, we: i) critically review current conceptualizations of bias in light of theoretical insights from related disciplines, ii) summarize previous analyses aimed at assessing gender bias in MT, iii) discuss the mitigating strategies proposed so far, and iv) point toward potential directions for future work.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Tversky, A., & Kahneman, D. (1974) · Science · doi:10.1126/science.185.4157.1124 · Cited by 28,810 · cited 1×
“In cognitive science, bias refers to the possible outcome of heuristics, that is, mental shortcuts that can be critical to support prompt reactions (Tversky and Kahneman, 1973, 1974).”
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Availability: A heuristic for judging frequency and probability
Tversky, A., & Kahneman, D. (1973) · Cognitive Psychology · doi:10.1016/0010-0285(73)90033-9 · Cited by 9,984
Crenshaw, K. (2018) · Feminist Legal Theory · doi:10.4324/9780429500480-5 · Cited by 9,510
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988 · cited 3×
“With language technologies entering widespread use and being deployed at a massive scale, their societal impact has raised concern both within (Hovy and Spruit, 2016; Bender et al., 2021) and outside (Dastin, 2018) the scientific community.”
BackgroundMethodA Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2019) · arXiv · doi:10.48550/arxiv.1908.09635 · Cited by 5,812
Dwork, C., Hardt, M., Pitassi, T., Reingold, O., & Zemel, R. (2012) · Proceedings of the 3rd Innovations in Theoretical Computer Science Conference · doi:10.1145/2090236.2090255 · Cited by 3,501
Shortcut learning in deep neural networks
Geirhos, R., Jacobsen, J.-H., Michaelis, C., Zemel, R., Brendel, W., Bethge, M., & Wichmann, F. A. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-00257-z · Cited by 2,224
D'Ignazio, C., & Klein, L. F. (2020) · doi:10.7551/mitpress/11805.001.0001 · Cited by 1,738
Fairness and Abstraction in Sociotechnical Systems
Selbst, A. D., Boyd, D., Friedler, S. A., Venkatasubramanian, S., & Vertesi, J. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287598 · Cited by 1,631
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
Bolukbasi, T., Chang, K.-W., Zou, J., Saligrama, V., & Kalai, A. (2016) · arXiv · doi:10.48550/arxiv.1607.06520 · Cited by 1,615
Gender As a Social Structure: Theory Wrestling with Activism
Risman, B. J. (2004) · Gender & Society · doi:10.1177/0891243204265349 · Cited by 1,451
Corbett, G. G. (1991) · doi:10.1017/cbo9781139166119 · Cited by 1,385
Rahwan, I., Cebrian, M., Obradovich, N., Bongard, J., Bonnefon, J.-F., Breazeal, C., Crandall, J. W., Christakis, N. A., Couzin, I. D., Jackson, M. O., et al. (2019) · Nature · doi:10.1038/s41586-019-1138-y · Cited by 1,364
Friedman, B., & Nissenbaum, H. (1996) · ACM Transactions on Information Systems · doi:10.1145/230538.230561 · Cited by 1,203 · cited 1×
“Hereby, drawing on the human-centered approach of Value Sensitive Design (Friedman and Hendry, 2019), we consider as biased an MT model that systematically and unfairly discriminates against certain individuals or groups in favour of others (Friedman and Nissenbaum, 1996).”
MethodAmazon Scraps Secret AI Recruiting Tool that Showed Bias against Women *
Dastin, J. (2022) · Ethics of Data and Analytics · doi:10.1201/9781003278290-44 · Cited by 1,165
Language (Technology) is Power: A Critical Survey of “Bias” in NLP
Blodgett, S. L., Barocas, S., Daumé III, H., & Wallach, H. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.485 · Cited by 1,050 · cited 1×
“While technical countermeasures are needed, failing to adopt a wider perspective and engage with related literature outside of NLP can be detrimental to the advancement of the field (Blodgett et al., 2020).”
BackgroundBender, E. M., & Friedman, B. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00041 · Cited by 854 · cited 1×
“Since this can lead to systematic errors and/or adverse social effects, bias investigation is not only a scientific and technical endeavor but also an ethical one, given the growing societal role of NLP applications (Bender and Friedman, 2018).”
BackgroundMen Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
Zhao, J., Wang, T., Yatskar, M., Ordonez, V., & Chang, K.-W. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1323 · Cited by 829 · cited 1×
“Sometimes, for example, coreference resolution systems fail to recognize women doctors (Zhao et al., 2017; Rudinger et al., 2018), image captioning models do not detect women sitting next to a computer (Hendricks et al.”
BackgroundGender differences in language use: An analysis of 14,000 text samples
Newman, M. L., Groom, C. J., Handelman, L. D., & Pennebaker, J. W. (2008) · Discourse Processes · doi:10.1080/01638530802073712 · Cited by 788 · cited 1×
“For instance, it opts for think rather than believe, which is in concordance with corpus studies claiming a tendency for women to use less assertive speech (Newman et al., 2008).”
ResultNon-binary or genderqueer genders
Richards, C., Bouman, W. P., Seal, L., Barker, M. J., Nieder, T. O., & T’Sjoen, G. (2016) · International Review of Psychiatry · doi:10.3109/09540261.2015.1106446 · Cited by 782 · cited 1×
“For the recognition of non-binary groups (Richards et al., 2016), we invite studies on how such modeling could be integrated with neutral strategies (§6).”
MethodGender bias in coreference resolution: Evaluation and debiasing methods
Zhao, J., Wang, T., Yatskar, M., Ordonez, V., & Chang, K.-W. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2003 · Cited by 684 · cited 1×
“(2019) created WinoMT by concatenating two existing English GBETs for coreference resolution (Rudinger et al., 2018; Zhao et al., 2018a).”
MethodData and its (dis)contents: A survey of dataset development and use in machine learning research
Paullada, A., Raji, I. D., Bender, E. M., Denton, E., & Hanna, A. (2021) · Patterns · doi:10.1016/j.patter.2021.100336 · Cited by 548 · cited 1×
“Since datasets are a crucial source of bias, it is also crucial to advocate for a careful data curation (Mehrabi et al., 2019; Paullada et al., 2020; Hanna et al., 2021; Bender et al., 2021), guided by pragmatically”
BackgroundWords of wisdom: Language use over the life span
Pennebaker, J. W., & Stone, L. D. (2003) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.85.2.291 · Cited by 518
The Misgendering Machines: Trans/HCI Implications of Automatic Gender Recognition
Keyes, O. (2018) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3274357 · Cited by 505
Mitigating Gender Bias in Natural Language Processing: Literature Review
Sun, T., Gaut, A., Tang, S., Huang, Y., ElSherief, M., Zhao, J., Mirza, D., Belding, E., Chang, K.-W., & Wang, W. Y. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1159 · Cited by 492
Gonen, H., & Goldberg, Y. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1061 · Cited by 454
Gender Bias in Coreference Resolution
Rudinger, R., Naradowsky, J., Leonard, B., & Van Durme, B. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2002 · Cited by 443 · cited 2×
“Sometimes, for example, coreference resolution systems fail to recognize women doctors (Zhao et al., 2017; Rudinger et al., 2018), image captioning models do not detect women sitting next to a computer (Hendricks et al.”
BackgroundMethodAssessing gender bias in machine translation: a case study with Google Translate
Prates, M. O. R., Avelar, P. H., & Lamb, L. C. (2020) · Neural Computing and Applications · doi:10.1007/s00521-019-04144-6 · Cited by 410
Assessing Gender Bias in Machine Translation -- A Case Study with Google Translate
Prates, M. O. R., Avelar, P. H. C., & Lamb, L. (2018) · arXiv · doi:10.48550/arxiv.1809.02208 · Cited by 409
Women Also Snowboard: Overcoming Bias in Captioning Models
Hendricks, L. A., Burns, K., Saenko, K., Darrell, T., & Rohrbach, A. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01219-9_47 · Cited by 404
Jacobs, A. Z., & Wallach, H. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445901 · Cited by 362 · cited 2×
“For a broader discussion on measurement and bias we refer the reader also to (Jacobs, 2021; Jacobs et al., 2020).”
BackgroundGender and Dialect Bias in YouTube’s Automatic Captions
Tatman, R. (2017) · Proceedings of the First ACL Workshop on Ethics in Natural Language Processing · doi:10.18653/v1/w17-1606 · Cited by 338
The social impact of natural language processing
Hovy, D., & Spruit, S. L. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/p16-2096 · Cited by 329
Hacker, P. (2018) · Common Market Law Review · doi:10.54648/cola2018095 · Cited by 317
Geva, M., Goldberg, Y., & Berant, J. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1107 · Cited by 284 · cited 1×
“This means starting from bottom-level countermeasures, engaging with translators (De Marco and Toto, 2019; Lessinger, 2020) and annotators (Waseem, 2016; Geva et al., 2019), and considering everyone’s subjective positionality—and, crucially, also the lack of diversity within technology teams (Schluter, 2018; Waseem et…”
BackgroundPredictive biases in natural language processing models: A conceptual framework and overview
Shah, D. S., Schwartz, H. A., & Hovy, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.468 · Cited by 241 · cited 2×
“, 2019) and conceived bias as the divergence from an ideal or expected value (Glymour and Herington, 2019; Shah et al., 2020), which can occur if models rely on spurious cues and unintended shortcut strategies to predict outputs (Schuster et al.”
BackgroundTowards Debiasing Fact Verification Models
Schuster, T., Shah, D., Yeo, Y. J. S., Roberto Filizzola Ortiz, D., Santus, E., & Barzilay, R. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1341 · Cited by 171 · cited 1×
“, 2020), which can occur if models rely on spurious cues and unintended shortcut strategies to predict outputs (Schuster et al., 2019; McCoy et al., 2019; Geirhos et al., 2020).”
BackgroundLindqvist, A., Renström, E. A., & Gustafsson Sendén, M. (2019) · Sex Roles · doi:10.1007/s11199-018-0974-9 · Cited by 134
Beukeboom, C. J., & Burgers, C. (2019) · Review of Communication Research · doi:10.12840/issn.2255-4165.017 · Cited by 126
Masculine Bias in the Attribution of Personhood: People = Male, Male = People
Hamilton, M. C. (1991) · Psychology of Women Quarterly · doi:10.1111/j.1471-6402.1991.tb00415.x · Cited by 120
Gebru, T. (2020) · The Oxford Handbook of Ethics of AI · doi:10.1093/oxfordhb/9780190067397.013.16 · Cited by 111
Gender as a Variable in Natural-Language Processing: Ethical Considerations
Larson, B. (2017) · Proceedings of the First ACL Workshop on Ethics in Natural Language Processing · doi:10.18653/v1/w17-1601 · Cited by 111 · cited 1×
“However, using personal gender as a variable requires a prior understanding of which categories may be salient, and a critical reflection on how gender is intended and ascribed (Larson, 2017).”
BackgroundLessons for artificial intelligence from the study of natural stupidity
Rich, A. S., & Gureckis, T. M. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0038-z · Cited by 94
Diversity and Inclusion Metrics in Subset Selection
Mitchell, M., Baker, D., Moorosi, N., Denton, R., Hutchinson, B., Hanna, A., Gebru, T., & Morgenstern, J. (2020) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3375627.3375832 · Cited by 87
A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle
Suresh, H., & Guttag, J. (2021) · Equity and Access in Algorithms, Mechanisms, and Optimization · doi:10.1145/3465416.3483305 · Cited by 82
A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle
Suresh, H., & Guttag, J. V. (2019) · arXiv · doi:10.48550/arxiv.1901.10002 · Cited by 82
Glymour, B., & Herington, J. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287573 · Cited by 50 · cited 1×
“, 2019) and conceived bias as the divergence from an ideal or expected value (Glymour and Herington, 2019; Shah et al., 2020), which can occur if models rely on spurious cues and unintended shortcut strategies to predict outputs (Schuster et al.”
BackgroundGarimella, A., Banea, C., Hovy, D., & Mihalcea, R. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1339 · Cited by 41
Intrinsic bias metrics do not correlate with application bias
Goldfarb-Tarrant, S., Marchant, R., Muñoz Sánchez, R., Pandya, M., & Lopez, A. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.150 · Cited by 33
Cited by
Societal Biases in Language Generation: Progress and Challenges
Sheng, E., Chang, K.-W., Natarajan, P., & Peng, N. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.330 · Cited by 131
Czarnowska, P., Vyas, Y., & Shah, K. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00425 · Cited by 72
“There are also many task specific surveys, e.g., for language generation (Sheng et al., 2021) or machine translation (Savoldi et al., 2021).”
BackgroundTheories of ”gender” in NLP bias research
Devinney, H., Björklund, J., & Björklund, H. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3534627 · Cited by 49
Seamless: Multilingual Expressive and Streaming Speech Translation
Communication, S., Barrault, L., Chung, Y.-A., Meglioli, M. C., Dale, D., Dong, N., Duppenthaler, M., Duquenne, P.-A., Ellis, B., Elsahar, H., et al. (2023) · arXiv · doi:10.48550/arxiv.2312.05187 · Cited by 45
Accelerating Transformer Inference for Translation via Parallel Decoding
Santilli, A., Severino, S., Postolache, E., Maiorca, V., Mancusi, M., Marin, R., & Rodola, E. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.689 · Cited by 29
“…indeed shows how DDG viz can be used to highlight possible biases encoded in the model as it is not clear how the model can be so confident (see cell probability) that after "satis-fied" the most straightforward tokens to decode are "Romanian couples" (Chang et al., 2019; Savoldi et al., 2021).”
Background
Metadata
- Authors
- Savoldi, B., Gaido, M., Bentivogli, L., Negri, M., & Turchi, M.
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press
- Published
- 2021
- Volume
- 9
- Pages
- 845-874
- ISSN
- 2307-387X (ISSN-L)
- OpenAlex
- W3156775540
- Cited by
- 165
- References
- 50
- FWCI
- 32.44
- Type
- journal article
- Language
- en
- Open access
- diamond
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.