# How does Grammatical Gender Affect Noun Representations in Gender-Marking Languages?

arXiv: https://arxiv.org/abs/1910.14161 · HTML: https://mlsanity.com/paper/1910.14161/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2019.

## Built on by (most cited first, 14 of 14)

- [Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation](https://mlsanity.com/paper/2203.09866/) (2022)
- [Evaluating Gender Bias in Hindi-English Machine Translation](https://mlsanity.com/paper/2106.08680/) (2021)
- [Naturalistic Causal Probing for Morpho-Syntax](https://mlsanity.com/paper/2205.07043/) (2022)
- [Fairness in Language Models Beyond English: Gaps and Challenges](https://mlsanity.com/paper/2302.12578/) (2023)
- [Analyzing Gender Representation in Multilingual Models](https://mlsanity.com/paper/2204.09168/) (2022)
- [Measuring Gender Bias in Word Embeddings of Gendered Languages Requires Disentangling Grammatical Gender Signals](https://mlsanity.com/paper/2206.01691/) (2022)
- [Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora](https://mlsanity.com/paper/2406.13677/) (2024)
- [Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis](https://mlsanity.com/paper/2305.12709/) (2023)
- [A methodology to characterize bias and harmful stereotypes in natural language processing in Latin America](https://mlsanity.com/paper/2207.06591/) (2022)
- [Understanding or Memorizing? A Case Study of German Definite Articles in Language Models](https://mlsanity.com/paper/2601.09313/) (2026)
- [Revisiting The Classics: A Study on Identifying and Rectifying Gender Stereotypes in Rhymes and Poems](https://mlsanity.com/paper/2403.11752/) (2024)
- [MORPHOGEN: A Multilingual Benchmark for Evaluating Gender-Aware Morphological Generation](https://mlsanity.com/paper/2604.18914/) (2026)
- [Is She Even Relevant? When BERT Ignores Explicit Gender Cues](https://mlsanity.com/paper/2605.07622/) (2026)
- [Estimating Grammatical Gender Directions in Contextual Embeddings under Controlled and Natural Contexts](https://mlsanity.com/paper/2606.30152/) (2026)

## Abstract (arXiv)

Many natural languages assign grammatical gender also to inanimate nouns in the language. In such languages, words that relate to the gender-marked nouns are inflected to agree with the noun's gender. We show that this affects the word representations of inanimate nouns, resulting in nouns with the same gender being closer to each other than nouns with different gender. While "embedding debiasing" methods fail to remove the effect, we demonstrate that a careful application of methods that neutralize grammatical gender signals from the words' context when training word embeddings is effective in removing it. Fixing the grammatical gender bias yields a positive effect on the quality of the resulting word embeddings, both in monolingual and cross-lingual settings. We note that successfully removing gender signals, while achievable, is not trivial to do and that a language-specific morphological analyzer, together with careful usage of it, are essential for achieving good results.