Measuring Gender Bias in Word Embeddings across Domains and Discovering New Gender Bias Word Categories
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Prior work has shown that word embeddings capture human stereotypes, including gender bias.However, there is a lack of studies testing the presence of specific gender bias categories in word embeddings across diverse domains.This paper aims to fill this gap by applying the WEAT bias detection method to four sets of word embeddings trained on corpora from four different domains: news, social networking, biomedical and a gender-balanced corpus extracted from Wikipedia (GAP).We find that some domains are definitely more prone to gender bias than others, and that the categories of gender bias present also vary for each set of word embeddings.We detect some gender bias in GAP.We also propose a simple but novel method for discovering new bias categories by clustering word embeddings.We validate this method through WEAT's hypothesis testing mechanism and find it useful for expanding the relatively small set of wellknown gender bias word categories commonly used in the literature.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
(2007) · doi:10.5555/1283383.1283494 · Cited by 7,364
Harris, Z. S. (1954) · WORD · doi:10.1080/00437956.1954.11659520 · Cited by 4,807
Sex, gender, and pain: a review of recent clinical and experimental findings
Fillingim, R. B., King, C. D., Ribeiro-Dasilva, M. C., Rahim-Williams, B., & Riley, J. L. (2009) · The Journal of Pain · doi:10.1016/j.jpain.2008.12.001 · Cited by 2,766
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
Bolukbasi, T., Chang, K.-W., Zou, J., Saligrama, V., & Kalai, A. (2016) · arXiv · doi:10.48550/arxiv.1607.06520 · Cited by 1,615 · cited 2×
“One approach is debiasing learnt corpora (Bolukbasi et al., 2016), which is achieved using algorithms that modify word embeddings in such a way that neutralises stereotypical co-sine similarities.”
BackgroundWord embeddings quantify 100 years of gender and ethnic stereotypes
Garg, N., Schiebinger, L., Jurafsky, D., & Zou, J. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1720347115 · Cited by 1,065 · cited 4×
“Although one would hope to find little gender bias in a news corpus, given that its authors are professional journalists, bias had already been detected by Caliskan et al. (2017) and Garg et al. (2018) using methods similar to ours.”
BackgroundResultInfluentialNeural Network Methods for Natural Language Processing
Goldberg, Y. (2017) · Synthesis Lectures on Human Language Technologies · doi:10.1007/978-3-031-02165-7 · Cited by 821 · cited 3×
“It is known that window size affects semantic similarity: larger window sizes tend to capture broader, more topical similarities between words whilst smaller windows capture more linguistic or even syntactic similarities (Goldberg, 2017, Sec.”
BackgroundInfluentialMeasuring and Mitigating Unintended Bias in Text Classification
Dixon, L., Li, J., Sorensen, J., Thain, N., & Vasserman, L. (2018) · Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3278721.3278729 · Cited by 674 · cited 3×
“, 2018), while abusive online language detection systems have been observed to produce false positives on terms associated with minorities and women (Dixon et al., 2018; Park et al., 2018).”
BackgroundReducing Gender Bias in Abusive Language Detection
Park, J. H., Shin, J., & Fung, P. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1302 · Cited by 323 · cited 1×
“…when these ranking algorithms take demographic features into account (directly or indirectly) (Chen et al., 2018), while abusive online language detection systems have been observed to produce false positives on terms associated with minorities and women (Dixon et al., 2018; Park et al., 2018).”
BackgroundMind the GAP: A balanced corpus of gendered ambiguous pronouns
Webster, K., Recasens, M., Axelrod, V., & Baldridge, J. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00240 · Cited by 223
Investigating the Impact of Gender on Rank in Resume Search Engines
Chen, L., Ma, R., Hannák, A., & Wilson, C. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174225 · Cited by 155 · cited 1×
“…produce rankings that disadvantage some candidates, when these ranking algorithms take demographic features into account (directly or indirectly) (Chen et al., 2018), while abusive online language detection systems have been observed to produce false positives on terms associated with minorities…”
Background
Cited by
Language (Technology) is Power: A Critical Survey of “Bias” in NLP
Blodgett, S. L., Barocas, S., Daumé III, H., & Wallach, H. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.485 · Cited by 1,050
“…et al. (2018); Thelwall (2018); Zhao et al. (2018b); Badjatiya et al. (2019); Bagdasaryan et al. (2019); Bamman et al. (2019); Cao and Daumé (2019); Chaloner and Maldonado (2019); Cho et al. (2019); Davidson et al. (2019); De-Arteaga et al. (2019); Fisher (2019); Font and Costa-jussà (2019);…”
BackgroundInfluentialGarrido-Muñoz, I., Montejo-Ráez, A., Martínez-Santiago, F., & Ureña-López, L. A. (2021) · Applied Sciences · doi:10.3390/app11073184 · Cited by 123
HONEST: Measuring Hurtful Sentence Completion in Language Models
Nozza, D., Bianchi, F., & Hovy, D. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.191 · Cited by 95
Czarnowska, P., Vyas, Y., & Shah, K. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00425 · Cited by 72
Kaplan, D. M., Palitsky, R., Arconada Alvarez, S. J., Pozzo, N. S., Greenleaf, M. N., Atkinson, C. A., & Lam, W. A. (2024) · Journal of Medical Internet Research · doi:10.2196/51837 · Cited by 55
“…these tools in mitigating bias is commonly assessed through word vector associations tests that measure how closely associated specific words or phrases are with respect to sets of attribute words such as “male” versus “female” [35,36] (although other measures of association exist as well [37-39]).”
Metadata
- Authors
- Chaloner, K., & Maldonado, A.
- Venue
- Proceedings of the First Workshop on Gender Bias in Natural Language Processing
- Published
- 2019
- Pages
- 25-32
- OpenAlex
- W2972423177
- Cited by
- 50
- References
- 10
- FWCI
- 10.10
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Measuring Gender Bias in Word Embeddings across Domains and Discovering New Gender Bias Word Categories. https://app.cochat.ai/papers/10.18653/v1/w19-3804
- The paper
- Chaloner, K., & Maldonado, A. (2019). Measuring Gender Bias in Word Embeddings across Domains and Discovering New Gender Bias Word Categories. Proceedings of the First Workshop on Gender Bias in Natural Language Processing. https://doi.org/10.18653/v1/w19-3804
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.