---
title: "Evaluating Gender Bias in Machine — Stanovsky 2019"
description: "Machine translation from English into languages with grammatical gender often forces a system to decide a person's gender."
authors: ["Gabriel Stanovsky", "Noah A. Smith", "Luke Zettlemoyer"]
year: 2019
venue: "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics"
source: "https://aclanthology.org/P19-1164/"
doi: "10.18653/v1/p19-1164"
arxiv: "1906.00591"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/stanovsky-2019-evaluating-gender-bias-machine-translation/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/stanovsky-2019-evaluating-gender-bias-machine-translation/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2019](https://md.research.elamur.ai/free/en/papers/2019/page/2/) / Evaluating Gender Bias in Machine Translation

# Evaluating Gender Bias in Machine Translation

**Authors:** [Gabriel Stanovsky](https://md.research.elamur.ai/free/en/authors/gabriel-stanovsky/), [Noah A. Smith](https://md.research.elamur.ai/free/en/authors/noah-a-smith/), [Luke Zettlemoyer](https://md.research.elamur.ai/free/en/authors/luke-zettlemoyer/) · **Institutions:** [University of Washington](https://md.research.elamur.ai/free/en/universities/university-of-washington/) · [Allen Institute for Artificial Intelligence](https://md.research.elamur.ai/free/en/labs/allen-institute-for-artificial-intelligence/) · **Year:** 2019 · **Venue:** Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/P19-1164/) · [PDF](https://aclanthology.org/P19-1164.pdf) · [DOI 10.18653/v1/p19-1164](https://doi.org/10.18653/v1/p19-1164) · [arXiv 1906.00591](https://arxiv.org/abs/1906.00591) · [OpenAlex](https://openalex.org/W2947599143)

**Citations:** 292 citations (OpenAlex, 2026-10-14) · [296](https://md.research.elamur.ai/free/en/papers/stanovsky-2019-evaluating-gender-bias-machine-translation/cited-by/) in our library, of the 140884 papers whose bibliographies we read

## Summary
Machine translation from English into languages with grammatical gender often forces a system to decide a person's gender. This paper checks whether that decision follows the context or falls back on occupational stereotypes. The authors built WinoMT, a challenge set made by joining the Winogender and WinoBias coreference test sets. In these English sentences, a pronoun reveals the gender of someone named only by their job, and the roles are often cast against stereotype, such as a female doctor. The evaluation needs no reference translations. Each sentence is translated, fast_align links the source entity to its counterpart in the output, and off-the-shelf morphological analyzers read the gender of the translated entity. The method was applied to eight target languages, four commercial MT services and two state-of-the-art Fairseq research models. Every system turned out to be clearly gender-biased. Accuracy was often close to chance, and results were consistently worse for female and anti-stereotypical roles. The benchmark and code are public and can be extended, and Ukrainian and Russian are among the languages covered.

## Key points
- **WinoMT:** 3,888 instances, balanced between male and female and between stereotypical and anti-stereotypical role assignments. Data and code are at github.com/gabrielStanovsky/mt_gender.
- **Coverage:** eight target languages (Spanish, French, Italian, Russian, Ukrainian, Hebrew, Arabic, German). Systems tested were Google Translate, Microsoft Translator, Amazon Translate (it had no Ukrainian model), SYSTRAN, and the Ott et al. (2018) and Edunov et al. (2018) models. Morphology tools included spaCy, Korobov's analyzer for Russian and Ukrainian, and a ta marbuta check for Arabic.
- **Metrics:** gender accuracy, ΔG (male–female F1 gap) and ΔS (pro- vs. anti-stereotypical F1 gap). German scored best for most systems. Google Translate reached only 38.4% accuracy on Ukrainian and 37.7% on Russian.
- **Adjective test:** adding "handsome" or "pretty" before the entity raised Google Translate's accuracy by +10.4 points for Spanish, +11.2 for Russian and +4.5 for Ukrainian. This only works with oracle coreference, so it is not a practical fix.
- **Human check:** native speakers made 9,600 annotations. They agreed with the automatic method 87% of the time on average, against 90% agreement between annotators.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Machine translation](https://md.research.elamur.ai/free/en/shelves/machine-translation/)

Topics: [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{stanovsky2019evaluating,
  title = {{Evaluating Gender Bias in Machine Translation}},
  author = {Stanovsky, Gabriel and Smith, Noah A. and Zettlemoyer, Luke},
  booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
  year = {2019},
  doi = {10.18653/v1/p19-1164},
  eprint = {1906.00591},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/p19-1164}
}
```

- [← previous WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://md.research.elamur.ai/free/en/papers/pilehvar-2019-wic-word-context-dataset-evaluating/)
- [next → Measuring Bias in Contextualized Word Representations](https://md.research.elamur.ai/free/en/papers/kurita-2019-measuring-bias-contextualized-word-representations/)
- [↑ back to papers of 2019](https://md.research.elamur.ai/free/en/papers/2019/page/2/)

## References

28 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Meni Adler and Michael Elhadad. 2006. An unsupervised morpheme-based HMM for Hebrew morphological disambiguation. In ACL. [find](https://scholar.google.com/scholar?q=Meni+Adler+and+Michael+Elhadad%2E+2006%2E+An+unsupervised+morpheme%2Dbased+HMM+for+Hebrew+morphological+disambiguation%2E+In+ACL%2E) [our card](https://md.research.elamur.ai/free/en/papers/aclbulk-2006-adler-unsupervised-morpheme-based-hmm-hebrew/)
2. Duygu Altinok. 2018. DEMorphy, German language morphological analyzer. CoRR, abs/1803.00902. [↗](https://arxiv.org/abs/1803.00902)
3. David Alvarez-Melis and Tommi S. Jaakkola. 2017. A causal framework for explaining the predictions of black-box sequence-to-sequence models. In EMNLP. [find](https://scholar.google.com/scholar?q=David+Alvarez%2DMelis+and+Tommi+S%2E+Jaakkola%2E+2017%2E+A+causal+framework+for+explaining+the+predictions+of+black%2Dbox+sequence%2Dto%2Dsequence+models%2E+In+EMNLP%2E)
4. Rachel Bawden, Rico Sennrich, Alexandra Birch, and Barry Haddow. 2018. Evaluating discourse phenomena in neural machine translation. In NAACL-HLT. [find](https://scholar.google.com/scholar?q=Rachel+Bawden%2C+Rico+Sennrich%2C+Alexandra+Birch%2C+and+Barry+Haddow%2E+2018%2E+Evaluating+discourse+phenomena+in+neural+machine+translation%2E+In+NAACL%2DHLT%2E) [our card](https://md.research.elamur.ai/free/en/papers/bawden-2017-evaluating-discourse-phenomena-neural-machine/)
5. Tolga Bolukbasi, Kai-Wei Chang, James Y. Zou, Venkatesh Saligrama, and Adam Tauman Kalai. 2016. Man is to computer programmer as woman is to homemaker? debiasing word embeddings. In NIPS. [find](https://scholar.google.com/scholar?q=Tolga+Bolukbasi%2C+Kai%2DWei+Chang%2C+James+Y%2E+Zou%2C+Venkatesh+Saligrama%2C+and+Adam+Tauman+Kalai%2E+2016%2E+Man+is+to+computer+programmer+as+woman+is+to+homemaker%3F+debiasing+word+embeddings%2E+In+NIPS%2E) [our card](https://md.research.elamur.ai/free/en/papers/bolukbasi-2016-man-computer-programmer-woman-homemaker/)
6. Aljoscha Burchardt, Vivien Macketanz, Jon Dehdari, Georg Heigold, Jan-Thorsten Peter, and Philip Williams. 2017. A linguistic evaluation of rule-based, phrase-based, and neural mt engines. The Prague Bulletin of Mathematical Linguistics, 108(1):159–170. [find](https://scholar.google.com/scholar?q=Aljoscha+Burchardt%2C+Vivien+Macketanz%2C+Jon+Dehdari%2C+Georg+Heigold%2C+Jan%2DThorsten+Peter%2C+and+Philip+Williams%2E+2017%2E+A+linguistic+evaluation+of+rule%2Dbased%2C+phrase%2Dbased%2C+and+neural+mt+engines%2E+The+Prague+)
7. Matthew Honnibal and Ines Montani. 2017. spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing. To appear. [find](https://scholar.google.com/scholar?q=Matthew+Honnibal+and+Ines+Montani%2E+2017%2E+spaCy+2%3A+Natural+language+understanding+with+Bloom+embeddings%2C+convolutional+neural+networks+and+incremental+parsing%2E+To+appear%2E)
8. Pierre Isabelle, Colin Cherry, and George F. Foster. 2017. A challenge set approach to evaluating machine translation. In EMNLP. [find](https://scholar.google.com/scholar?q=Pierre+Isabelle%2C+Colin+Cherry%2C+and+George+F%2E+Foster%2E+2017%2E+A+challenge+set+approach+to+evaluating+machine+translation%2E+In+EMNLP%2E) [our card](https://md.research.elamur.ai/free/en/papers/isabelle-2017-challenge-set-approach-evaluating-machine/)
9. Mikhail Korobov. 2015. Morphological analyzer and generator for Russian and Ukrainian languages. In Mikhail Yu. Khachay, Natalia Konstantinova, Alexander Panchenko, Dmitry I. Ignatov, and Valeri G. Labunets, editors, Analysis of Images, Social Networks and Texts, volume 542 of Communications in Computer and Information Science, pages 320– 332. Springer International Publishing. [find](https://scholar.google.com/scholar?q=Mikhail+Korobov%2E+2015%2E+Morphological+analyzer+and+generator+for+Russian+and+Ukrainian+languages%2E+In+Mikhail+Yu%2E+Khachay%2C+Natalia+Konstantinova%2C+Alexander+Panchenko%2C+Dmitry+I%2E+Ignatov%2C+and+Valeri+G%2E+La)
10. James Kuczmarski. 2018. Reducing gender bias in google translate. [find](https://scholar.google.com/scholar?q=James+Kuczmarski%2E+2018%2E+Reducing+gender+bias+in+google+translate%2E)
11. Hector J. Levesque. 2011. The Winograd schema challenge. In AAAI Spring Symposium: Logical Formalizations of Commonsense Reasoning. [find](https://scholar.google.com/scholar?q=Hector+J%2E+Levesque%2E+2011%2E+The+Winograd+schema+challenge%2E+In+AAAI+Spring+Symposium%3A+Logical+Formalizations+of+Commonsense+Reasoning%2E)
12. Angelica Mucchi-Faina. 2005. Visible or influential? language reforms and gender (in) equality. Social Science Information, 44(1):189–215. [find](https://scholar.google.com/scholar?q=Angelica+Mucchi%2DFaina%2E+2005%2E+Visible+or+influential%3F+language+reforms+and+gender+%28in%29+equality%2E+Social+Science+Information%2C+44%281%29%3A189%E2%80%93215%2E)
13. Mathias Müller, Annette Rios, Elena Voita, and Rico Sennrich. 2018. A large-scale test set for the evaluation of context-aware pronoun translation in neural machine translation. CoRR, abs/1810.02268. [↗](https://arxiv.org/abs/1810.02268) [our card](https://md.research.elamur.ai/free/en/papers/muller-2018-large-scale-test-set-evaluation/)
14. Greville G Corbett. 2007. Gender and noun classes. [find](https://scholar.google.com/scholar?q=Greville+G+Corbett%2E+2007%2E+Gender+and+noun+classes%2E)
15. Colette G Craig. 1986. Noun Classes and Categorization: Proceedings of a Symposium on Categorization and Noun Classification, volume 7. John Benjamins Publishing Company. [find](https://scholar.google.com/scholar?q=Colette+G+Craig%2E+1986%2E+Noun+Classes+and+Categorization%3A+Proceedings+of+a+Symposium+on+Categorization+and+Noun+Classification%2C+volume+7%2E+John+Benjamins+Publishing+Company%2E)
16. Chris Dyer, Victor Chahuneau, and Noah A. Smith. 2013. A simple, fast, and effective reparameterization of ibm model 2. In HLT-NAACL. [find](https://scholar.google.com/scholar?q=Chris+Dyer%2C+Victor+Chahuneau%2C+and+Noah+A%2E+Smith%2E+2013%2E+A+simple%2C+fast%2C+and+effective+reparameterization+of+ibm+model+2%2E+In+HLT%2DNAACL%2E)
17. Sergey Edunov, Myle Ott, Michael Auli, and David Grangier. 2018. Understanding back-translation at scale. arXiv preprint arXiv:1808.09381. [↗](https://arxiv.org/abs/1808.09381)
18. Yanai Elazar and Yoav Goldberg. 2018. Adversarial removal of demographic attributes from text data. In EMNLP. [find](https://scholar.google.com/scholar?q=Yanai+Elazar+and+Yoav+Goldberg%2E+2018%2E+Adversarial+removal+of+demographic+attributes+from+text+data%2E+In+EMNLP%2E) [our card](https://md.research.elamur.ai/free/en/papers/elazar-2018-adversarial-removal-demographic-attributes-text/)
19. Joel Escudé Font and Marta R. Costa-Jussà. 2019. Equalizing gender biases in neural machine translation with word embeddings techniques. CoRR, abs/1901.03116. [↗](https://arxiv.org/abs/1901.03116)
20. Hila Gonen and Yoav Goldberg. 2019. Lipstick on a pig: Debiasing methods cover up systematic gender biases in word embeddings but do not remove them. HLT-NAACL. [find](https://scholar.google.com/scholar?q=Hila+Gonen+and+Yoav+Goldberg%2E+2019%2E+Lipstick+on+a+pig%3A+Debiasing+methods+cover+up+systematic+gender+biases+in+word+embeddings+but+do+not+remove+them%2E+HLT%2DNAACL%2E) [our card](https://md.research.elamur.ai/free/en/papers/gonen-2019-lipstick-pig-debiasing-methods-cover/)
21. John A Hawkins. 2015. A Comparative Typology of English and German: Unifying the Contrasts. Routledge. [find](https://scholar.google.com/scholar?q=John+A+Hawkins%2E+2015%2E+A+Comparative+Typology+of+English+and+German%3A+Unifying+the+Contrasts%2E+Routledge%2E)
22. Myle Ott, Sergey Edunov, David Grangier, and Michael Auli. 2018. Scaling neural machine translation. arXiv preprint arXiv:1806.00187. [↗](https://arxiv.org/abs/1806.00187) [our card](https://md.research.elamur.ai/free/en/papers/ott-2018-scaling-neural-machine-translation/)
23. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In ACL. [find](https://scholar.google.com/scholar?q=Kishore+Papineni%2C+Salim+Roukos%2C+Todd+Ward%2C+and+Wei%2DJing+Zhu%2E+2002%2E+Bleu%3A+a+method+for+automatic+evaluation+of+machine+translation%2E+In+ACL%2E) [our card](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/)
24. Rachel Rudinger, Chandler May, and Benjamin Van Durme. 2017. Social bias in elicited natural language inferences. In EthNLP@EACL. [find](https://scholar.google.com/scholar?q=Rachel+Rudinger%2C+Chandler+May%2C+and+Benjamin+Van+Durme%2E+2017%2E+Social+bias+in+elicited+natural+language+inferences%2E+In+EthNLP%40EACL%2E) [our card](https://md.research.elamur.ai/free/en/papers/rudinger-2017-social-bias-elicited-natural-language/)
25. Rachel Rudinger, Jason Naradowsky, Brian Leonard, and Benjamin Van Durme. 2018. Gender bias in coreference resolution. In NAACL-HLT. [find](https://scholar.google.com/scholar?q=Rachel+Rudinger%2C+Jason+Naradowsky%2C+Brian+Leonard%2C+and+Benjamin+Van+Durme%2E+2018%2E+Gender+bias+in+coreference+resolution%2E+In+NAACL%2DHLT%2E) [our card](https://md.research.elamur.ai/free/en/papers/rudinger-2018-gender-bias-coreference-resolution/)
26. Kellie Webster, Marta Recasens, Vera Axelrod, and Jason Baldridge. 2018. Mind the gap: A balanced corpus of gendered ambiguous pronouns. Transactions of the Association for Computational Linguistics, 6:605–617. [↗](https://doi.org/10.1162/tacl_a_00240) [our card](https://md.research.elamur.ai/free/en/papers/webster-2018-mind-gap-balanced-corpus-gendered/)
27. Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, and Kai-Wei Chang. 2017. Men also like shopping: Reducing gender bias amplification using corpus-level constraints. In EMNLP. [find](https://scholar.google.com/scholar?q=Jieyu+Zhao%2C+Tianlu+Wang%2C+Mark+Yatskar%2C+Vicente+Ordonez%2C+and+Kai%2DWei+Chang%2E+2017%2E+Men+also+like+shopping%3A+Reducing+gender+bias+amplification+using+corpus%2Dlevel+constraints%2E+In+EMNLP%2E) [our card](https://md.research.elamur.ai/free/en/papers/zhao-2017-men-also-like-shopping-reducing/)
28. Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, and Kai-Wei Chang. 2018. Gender bias in coreference resolution: Evaluation and debiasing methods. In NAACL-HLT. [find](https://scholar.google.com/scholar?q=Jieyu+Zhao%2C+Tianlu+Wang%2C+Mark+Yatskar%2C+Vicente+Ordonez%2C+and+Kai%2DWei+Chang%2E+2018%2E+Gender+bias+in+coreference+resolution%3A+Evaluation+and+debiasing+methods%2E+In+NAACL%2DHLT%2E) [our card](https://md.research.elamur.ai/free/en/papers/zhao-2018-gender-bias-coreference-resolution-evaluation/)