# Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem

arXiv: https://arxiv.org/abs/2004.04498 · HTML: https://mlsanity.com/paper/2004.04498/

## Key facts

- Cited by 86 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2020.

## Built on by (most cited first, 30 of 86)

- [Societal Biases in Language Generation: Progress and Challenges](https://mlsanity.com/paper/2105.04054/) (2021)
- [Gender Bias in Machine Translation](https://mlsanity.com/paper/2104.06001/) (2021)
- [A Survey on Fairness in Large Language Models](https://mlsanity.com/paper/2308.10149/) (2023)
- [A Survey on Gender Bias in Natural Language Processing](https://mlsanity.com/paper/2112.14168/) (2021)
- [Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics](https://mlsanity.com/paper/2106.14574/) (2021)
- [Bias in Large Language Models: Origin, Evaluation, and Mitigation](https://mlsanity.com/paper/2411.10915/) (2024)
- [Theories of "Gender" in NLP Bias Research](https://mlsanity.com/paper/2205.02526/) (2022)
- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [MT-GenEval: A Counterfactual and Contextual Dataset for Evaluating Gender Accuracy in Machine Translation](https://mlsanity.com/paper/2211.01355/) (2022)
- [Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems](https://mlsanity.com/paper/2310.05280/) (2023)
- [Balancing out Bias: Achieving Fairness Through Balanced Training](https://mlsanity.com/paper/2109.08253/) (2021)
- [Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization](https://mlsanity.com/paper/2210.04492/) (2022)
- [First the worst: Finding better gender translations during beam search](https://mlsanity.com/paper/2104.07429/) (2021)
- [Choose Your Lenses: Flaws in Gender Bias Evaluation](https://mlsanity.com/paper/2210.11471/) (2022)
- [Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation](https://mlsanity.com/paper/2106.00169/) (2021)
- [Sociodemographic Bias in Language Models: A Survey and Forward Path](https://mlsanity.com/paper/2306.08158/) (2023)
- [Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding](https://mlsanity.com/paper/2109.11708/) (2021)
- [Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation](https://mlsanity.com/paper/2203.09866/) (2022)
- [Gender Neutralization for an Inclusive Machine Translation: from Theoretical Foundations to Open Challenges](https://mlsanity.com/paper/2301.10075/) (2023)
- [What about em? How Commercial Machine Translation Fails to Handle (Neo-)Pronouns](https://mlsanity.com/paper/2305.16051/) (2023)
- [A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation](https://mlsanity.com/paper/2310.12127/) (2023)
- [Controlling Bias Exposure for Fair Interpretable Predictions](https://mlsanity.com/paper/2210.07455/) (2022)
- [Bias in News Summarization: Measures, Pitfalls and Corpora](https://mlsanity.com/paper/2309.08047/) (2023)
- [Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias](https://mlsanity.com/paper/2407.15366/) (2024)
- [GENder-IT: An Annotated English-Italian Parallel Challenge Set for Cross-Linguistic Natural Gender Phenomena](https://mlsanity.com/paper/2108.02854/) (2021)
- [Interactive-Chain-Prompting: Ambiguity Resolution for Crosslingual Conditional Generation with Interaction](https://mlsanity.com/paper/2301.10309/) (2023)
- [Examining Covert Gender Bias: A Case Study in Turkish and English Machine Translation Models](https://mlsanity.com/paper/2108.10379/) (2021)
- [What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Study](https://mlsanity.com/paper/2410.00545/) (2024)
- [Extending Challenge Sets to Uncover Gender Bias in Machine Translation: Impact of Stereotypical Verbs and Adjectives](https://mlsanity.com/paper/2107.11584/) (2021)
- [Adversarial Scrubbing of Demographic Information for Text Classification](https://mlsanity.com/paper/2109.08613/) (2021)

## Abstract (arXiv)

Training data for NLP tasks often exhibits gender bias in that fewer sentences refer to women than to men. In Neural Machine Translation (NMT) gender bias has been shown to reduce translation quality, particularly when the target language has grammatical gender. The recent WinoMT challenge set allows us to measure this effect directly (Stanovsky et al, 2019). Ideally we would reduce system bias by simply debiasing all data prior to training, but achieving this effectively is itself a challenge. Rather than attempt to create a `balanced' dataset, we use transfer learning on a small set of trusted, gender-balanced examples. This approach gives strong and consistent improvements in gender debiasing with much less computational cost than training from scratch. A known pitfall of transfer learning on new domains is `catastrophic forgetting', which we address both in adaptation and in inference. During adaptation we show that Elastic Weight Consolidation allows a performance trade-off between general translation quality and bias reduction. During inference we propose a lattice-rescoring scheme which outperforms all systems evaluated in Stanovsky et al (2019) on WinoMT with no degradation of general test set BLEU, and we show this scheme can be applied to remove gender bias in the output of `black box` online commercial MT systems. We demonstrate our approach translating from English into three languages with varied linguistic properties and data availability.