Estimating Grammatical Gender Directions in Contextual Embeddings under Controlled and Natural Contexts

• URL: http://arxiv.org/abs/2606.30152v1
• Date: Mon, 29 Jun 2026 11:29:05 GMT
• Title: Estimating Grammatical Gender Directions in Contextual Embeddings under Controlled and Natural Contexts
• Abstract summary: We make the first attempt to disentangle grammatical gender from semantic contamination for contextual embeddings.<n>We construct both controlled templates and natural Wikipedia contexts to build balanced datasets of inanimate nouns.<n>A set of dual-objective evaluation metrics is proposed to balance the suppression of grammatical gender leakage on inanimate nouns and the preservation of semantic gender distinctions for occupation terms.
• Score: 5.65924130016053
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Contextual language models conflate grammatical gender and social semantic bias in gendered languages such as Spanish. Existing gender debiasing approaches only operate on static word embeddings leaving contextual representations unexplored for this two dimensional gender disentanglement. To address the this issue, we make the first attempt to disentangle grammatical gender from semantic contamination for contextual embeddings. We construct both controlled templates and natural Wikipedia contexts to build balanced datasets of inanimate nouns, and design a framework equipped with centroid, Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA) gender direction estimators as well as contamination-aware weighting strategies. A set of dual-objective evaluation metrics is proposed to balance the suppression of grammatical gender leakage on inanimate nouns and the preservation of semantic gender distinctions for occupation terms. The results reveal that unweighted controlled contexts yield the purest grammatical gender direction, and the centroid estimator achieves better performance than discriminative baselines.

Related papers

• Lost in Translation? Exploring the Shift in Grammatical Gender from Latin to Occitan [2.321414033822442]
  We introduce an interpretable deep learning framework to investigate this phenomenon at both lexical and contextual levels.<n>We show that conventional tokenization strategies are insufficiently robust for this low-resource historical setting.<n>We quantify the contributions of different part-of-speech categories to grammatical gender prediction.
  arXiv  Detail & Related papers  (2026-05-09T20:36:49Z)
• GAMBIT+: A Challenge Set for Evaluating Gender Bias in Machine Translation Quality Estimation Metrics [18.766033854102663]
  Gender bias in machine translation (MT) systems has been extensively documented, but bias in automatic quality estimation (QE) metrics remains comparatively underexplored.<n>Existing studies suggest that QE metrics can also exhibit gender bias, yet most analyses are limited by small datasets, narrow occupational coverage, and restricted language variety.<n>We introduce a large-scale challenge set specifically designed to probe the behavior of QE metrics when evaluating translations containing gender-ambiguous occupational terms.
  arXiv  Detail & Related papers  (2025-10-08T10:09:03Z)
• Identifying Gender Stereotypes and Biases in Automated Translation from English to Italian using Similarity Networks [0.25049267048783647]
  This paper is a collaborative effort between Linguistics, Law, and Computer Science to evaluate stereotypes and biases in automated translation systems.<n>We advocate gender-neutral translation as a means to promote gender inclusion and improve the objectivity of machine translation.
  arXiv  Detail & Related papers  (2025-02-17T09:55:32Z)
• Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Words [85.48043537327258]
  Existing machine translation gender bias evaluations are primarily focused on male and female genders. This study presents a benchmark AmbGIMT (Gender-Inclusive Machine Translation with Ambiguous attitude words) We propose a novel process to evaluate gender bias based on the Emotional Attitude Score (EAS), which is used to quantify ambiguous attitude words.
  arXiv  Detail & Related papers  (2024-07-23T08:13:51Z)
• Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora [9.959039325564744]
  Large language models (LLMs) often inherit and amplify social biases embedded in their training data.<n>Gender bias is the association of specific roles or traits with a particular gender.<n>Gender representation bias is the unequal frequency of references to individuals of different genders.
  arXiv  Detail & Related papers  (2024-06-19T16:30:58Z)
• VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution [80.57383975987676]
  VisoGender is a novel dataset for benchmarking gender bias in vision-language models. We focus on occupation-related biases within a hegemonic system of binary gender, inspired by Winograd and Winogender schemas. We benchmark several state-of-the-art vision-language models and find that they demonstrate bias in resolving binary gender in complex scenes.
  arXiv  Detail & Related papers  (2023-06-21T17:59:51Z)
• Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous Pronouns [53.62845317039185]
  Bias-measuring datasets play a critical role in detecting biased behavior of language models. We propose a novel method to collect diverse, natural, and minimally distant text pairs via counterfactual generation. We show that four pre-trained language models are significantly more inconsistent across different gender groups than within each group.
  arXiv  Detail & Related papers  (2023-02-11T12:11:03Z)
• They, Them, Theirs: Rewriting with Gender-Neutral English [56.14842450974887]
  We perform a case study on the singular they, a common way to promote gender inclusion in English. We show how a model can be trained to produce gender-neutral English with 1% word error rate with no human-labeled data.
  arXiv  Detail & Related papers  (2021-02-12T21:47:48Z)
• Neural Machine Translation Doesn't Translate Gender Coreference Right Unless You Make It [18.148675498274866]
  We propose schemes for incorporating explicit word-level gender inflection tags into Neural Machine Translation. We find that simple existing approaches can over-generalize a gender-feature to multiple entities in a sentence. We also propose an extension to assess translations of gender-neutral entities from English given a corresponding linguistic convention.
  arXiv  Detail & Related papers  (2020-10-11T20:05:42Z)
• Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation [94.98656228690233]
  We propose a technique that purifies the word embeddings against corpus regularities prior to inferring and removing the gender subspace. Our approach preserves the distributional semantics of the pre-trained word embeddings while reducing gender bias to a significantly larger degree than prior approaches.
  arXiv  Detail & Related papers  (2020-05-03T02:33:20Z)
• Multi-Dimensional Gender Bias Classification [67.65551687580552]
  Machine learning models can inadvertently learn socially undesirable patterns when training on gender biased text. We propose a general framework that decomposes gender bias in text along several pragmatic and semantic dimensions. Using this fine-grained framework, we automatically annotate eight large scale datasets with gender information.
  arXiv  Detail & Related papers  (2020-05-01T21:23:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.