# Filling Gender & Number Gaps in Neural Machine Translation with Black-box Context Injection

arXiv: https://arxiv.org/abs/1903.03467 · HTML: https://mlsanity.com/paper/1903.03467/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2019.

## Built on by (most cited first, 27 of 27)

- [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 Gender Bias in Natural Language Processing](https://mlsanity.com/paper/2112.14168/) (2021)
- [XFORMAL: A Benchmark for Multilingual Formality Style Transfer](https://mlsanity.com/paper/2104.04108/) (2021)
- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender-Neutral Alternatives](https://mlsanity.com/paper/2109.06105/) (2021)
- [First the worst: Finding better gender translations during beam search](https://mlsanity.com/paper/2104.07429/) (2021)
- [Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation](https://mlsanity.com/paper/2203.09866/) (2022)
- [Investigating Failures of Automatic Translation in the Case of Unambiguous Gender](https://mlsanity.com/paper/2104.07838/) (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)
- [The Arabic Parallel Gender Corpus 2.0: Extensions and Analyses](https://mlsanity.com/paper/2110.09216/) (2021)
- [How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation](https://mlsanity.com/paper/2105.13782/) (2021)
- [Restoring Hebrew Diacritics Without a Dictionary](https://mlsanity.com/paper/2105.05209/) (2021)
- [Are We Paying Attention to Her? Investigating Gender Disambiguation and Attention in Machine Translation](https://mlsanity.com/paper/2505.08546/) (2025)
- [Improving Gender Translation Accuracy with Filtered Self-Training](https://mlsanity.com/paper/2104.07695/) (2021)
- [Towards Personalised and Document-level Machine Translation of Dialogue](https://mlsanity.com/paper/2102.10979/) (2021)
- [Gender Bias in Machine Translation and The Era of Large Language Models](https://mlsanity.com/paper/2401.10016/) (2024)
- [Controlling Extra-Textual Attributes about Dialogue Participants -- A Case Study of English-to-Polish Neural Machine Translation](https://mlsanity.com/paper/2205.04747/) (2022)
- [Gender Lost In Translation: How Bridging The Gap Between Languages Affects Gender Bias in Zero-Shot Multilingual Translation](https://mlsanity.com/paper/2305.16935/) (2023)
- [Faithful Target Attribute Prediction in Neural Machine Translation](https://mlsanity.com/paper/2109.12105/) (2021)
- ["Es geht um Respekt, nicht um Technologie": Erkenntnisse aus einem Interessensgruppen-"ubergreifenden Workshop zu genderfairer Sprache und Sprachtechnologie](https://mlsanity.com/paper/2209.02793/) (2022)
- [Evaluating and Improving the Coreference Capabilities of Machine Translation Models](https://mlsanity.com/paper/2302.08464/) (2023)
- [MTCue: Learning Zero-Shot Control of Extra-Textual Attributes by Leveraging Unstructured Context in Neural Machine Translation](https://mlsanity.com/paper/2305.15904/) (2023)
- [Current State-of-the-Art of Bias Detection and Mitigation in Machine Translation for African and European Languages: a Review](https://mlsanity.com/paper/2410.21126/) (2024)
- [Gender Disambiguation in Machine Translation: Diagnostic Evaluation in Decoder-Only Architectures](https://mlsanity.com/paper/2603.17952/) (2026)
- [Addressing the Blind Spots in Spoken Language Processing](https://mlsanity.com/paper/2309.06572/) (2023)
- [Cultural Fidelity in English-to-Hindi Translation: A Preservation-Fluency Frontier for Gender Recoverability](https://mlsanity.com/paper/2605.27654/) (2026)

## Abstract (arXiv)

When translating from a language that does not morphologically mark information such as gender and number into a language that does, translation systems must "guess" this missing information, often leading to incorrect translations in the given context. We propose a black-box approach for injecting the missing information to a pre-trained neural machine translation system, allowing to control the morphological variations in the generated translations without changing the underlying model or training data. We evaluate our method on an English to Hebrew translation task, and show that it is effective in injecting the gender and number information and that supplying the correct information improves the translation accuracy in up to 2.3 BLEU on a female-speaker test set for a state-of-the-art online black-box system. Finally, we perform a fine-grained syntactic analysis of the generated translations that shows the effectiveness of our method.