# Measuring Gender Bias in Word Embeddings of Gendered Languages Requires Disentangling Grammatical Gender Signals

arXiv: https://arxiv.org/abs/2206.01691 · HTML: https://mlsanity.com/paper/2206.01691/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 65 references that are in the map.
- First posted on arXiv 3 Jun 2022.

## Builds on (most cited first, 18 of 18)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://mlsanity.com/paper/1611.04558/) (2016)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [Learning Word Vectors for 157 Languages](https://mlsanity.com/paper/1802.06893/) (2018)
- [Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes](https://mlsanity.com/paper/1711.08412/) (2017)
- [Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology](https://mlsanity.com/paper/1906.04571/) (2019)
- [SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimation](https://mlsanity.com/paper/1408.3456/) (2014)
- [Understanding Undesirable Word Embedding Associations](https://mlsanity.com/paper/1908.06361/) (2019)
- [Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer](https://mlsanity.com/paper/2005.00699/) (2020)
- [Examining Gender Bias in Languages with Grammatical Gender](https://mlsanity.com/paper/1909.02224/) (2019)
- [Are We Consistently Biased? Multidimensional Analysis of Biases in Distributional Word Vectors](https://mlsanity.com/paper/1904.11783/) (2019)
- [ValNorm Quantifies Semantics to Reveal Consistent Valence Biases Across Languages and Over Centuries](https://mlsanity.com/paper/2006.03950/) (2020)
- [How does Grammatical Gender Affect Noun Representations in Gender-Marking Languages?](https://mlsanity.com/paper/1910.14161/) (2019)
- [Grammatical gender associations outweigh topical gender bias in crosslinguistic word embeddings](https://mlsanity.com/paper/2005.08864/) (2020)

## Built on by (most cited first, 5 of 5)

- [ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages](https://mlsanity.com/paper/2305.10510/) (2023)
- [Evaluating Biased Attitude Associations of Language Models in an Intersectional Context](https://mlsanity.com/paper/2307.03360/) (2023)
- [Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora](https://mlsanity.com/paper/2406.13677/) (2024)
- [The Causal Influence of Grammatical Gender on Distributional Semantics](https://mlsanity.com/paper/2311.18567/) (2023)
- [Estimating Grammatical Gender Directions in Contextual Embeddings under Controlled and Natural Contexts](https://mlsanity.com/paper/2606.30152/) (2026)

## Abstract (arXiv)

Does the grammatical gender of a language interfere when measuring the semantic gender information captured by its word embeddings? A number of anomalous gender bias measurements in the embeddings of gendered languages suggest this possibility. We demonstrate that word embeddings learn the association between a noun and its grammatical gender in grammatically gendered languages, which can skew social gender bias measurements. Consequently, word embedding post-processing methods are introduced to quantify, disentangle, and evaluate grammatical gender signals. The evaluation is performed on five gendered languages from the Germanic, Romance, and Slavic branches of the Indo-European language family. Our method reduces the strength of grammatical gender signals, which is measured in terms of effect size (Cohen's d), by a significant average of d = 1.3 for French, German, and Italian, and d = 0.56 for Polish and Spanish. Once grammatical gender is disentangled, the association between over 90% of 10,000 inanimate nouns and their assigned grammatical gender weakens, and cross-lingual bias results from the Word Embedding Association Test (WEAT) become more congruent with country-level implicit bias measurements. The results further suggest that disentangling grammatical gender signals from word embeddings may lead to improvement in semantic machine learning tasks.