Bias in word embeddings
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
Word embeddings are a widely used set of natural language processing techniques that map words to vectors of real numbers. These vectors are used to improve the quality of generative and predictive models. Recent studies demonstrate that word embeddings contain and amplify biases present in data, such as stereotypes and prejudice. In this study, we provide a complete overview of bias in word embeddings. We develop a new technique for bias detection for gendered languages and use it to compare bias in embeddings trained on Wikipedia and on political social media data. We investigate bias diffusion and prove that existing biases are transferred to further machine learning models. We test two techniques for bias mitigation and show that the generally proposed methodology for debiasing models at the embeddings level is insufficient. Finally, we employ biased word embeddings and illustrate that they can be used for the detection of similar biases in new data. Given that word embeddings are widely used by commercial companies, we discuss the challenges and required actions towards fair algorithmic implementations and applications.
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
Fee, D., & Fairclough, N. (1993) · Contemporary Sociology · doi:10.2307/2074659 · Cited by 11,611
The Ambivalent Sexism Inventory: Differentiating hostile and benevolent sexism.
Glick, P., & Fiske, S. T. (1996) · Journal of Personality and Social Psychology · doi:10.1037//0022-3514.70.3.491 · Cited by 5,202
The ethics of algorithms: Mapping the debate
Mittelstadt, B. D., Allo, P., Taddeo, M., Wachter, S., & Floridi, L. (2016) · Big Data & Society · doi:10.1177/2053951716679679 · Cited by 4,567 · cited 1×
“One of the issues research focuses on is algorithmic bias, which denotes the deviation of the algorithmic results from specific social expectations, based on epistemic or normative reasons [75].”
BackgroundExperiments in Intergroup Discrimination
Tajfel, H. (1970) · Scientific American · doi:10.1038/scientificamerican1170-96 · Cited by 2,577
European Union Regulations on Algorithmic Decision Making and a “Right to Explanation”
Goodman, B., & Flaxman, S. (2017) · AI Magazine · doi:10.1609/aimag.v38i3.2741 · Cited by 2,131 · cited 1×
“This will not only contribute towards fairness, but will provide the foundations for creating applications that respect the rights of social groups and individuals [43, 51].”
BackgroundFriedman, B., & Nissenbaum, H. (1996) · ACM Transactions on Information Systems · doi:10.1145/230538.230561 · Cited by 1,203 · cited 1×
“To do so, we adopt the Friedman et al. [38] proposed framework for analyzing algorithmic bias.”
MethodFairness definitions explained
Verma, S., & Rubin, J. (2018) · Proceedings of the International Workshop on Software Fairness · doi:10.1145/3194770.3194776 · Cited by 1,124
Word 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×
“Garg et al. [40] show how prejudice evolving over time is imprinted in word embeddings.”
BackgroundInfluentialGender Stereotypes and Attitudes Toward Women and Men
Eagly, A. H., & Mladinic, A. (1989) · Personality and Social Psychology Bulletin · doi:10.1177/0146167289154008 · Cited by 785 · cited 1×
“…of bias in word embeddings and further models, we restrict our study to the detection of forms of social discrimination that are detectable by concept comparison tests (e.g. the adjective check list [98], Implicit association test [49], Bem Sex-Role Inventory [56], polarity tests [31, 84]).”
MethodAI can be sexist and racist — it’s time to make it fair
Zou, J., & Schiebinger, L. (2018) · Nature · doi:10.1038/d41586-018-05707-8 · Cited by 765
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
“…Webster et al. (2019); Zmigrod et al. (2019); Gyamfi et al. (2020); Hube et al. (2020); Hutchinson et al. (2020); Kim et al. (2020); Nadeem et al. (2020); Papakyriakopoulos et al. (2020); Ravfogel et al. (2020); Rozado (2020); Sen and Ganguly (2020); Shin et al. (2020); Strengers et al. (2020).”
InfluentialTrustworthy ai: A computational perspective
Liu, H., Wang, Y., Fan, W., Liu, X., Li, Y., Jain, S., Liu, Y., Jain, A., & Tang, J. (2023) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3546872 · Cited by 261
Czarnowska, P., Vyas, Y., & Shah, K. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00425 · Cited by 72
“…(Bolukbasi et al., 2016; Caliskan et al., 2017; Kurita et al., 2019; Sedoc and Ungar, 2019; Chaloner and Maldon-ado, 2019; Dev and Phillips, 2019; Gonen and Goldberg, 2019; Hall Maudslay et al., 2019; Liang et al., 2020; Shin et al., 2020; Liang et al., 2020; Papakyriakopoulos et al., 2020).”
Theories of ”gender” in NLP bias research
Devinney, H., Björklund, J., & Björklund, H. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3534627 · Cited by 49
“[105] Orestis Papakyriakopoulos, Simon Hegelich, Juan Carlos, Medina Serrano, and Fabienne Marco.”
BackgroundSTILE: Exploring and Debugging Social Biases in Pre-trained Text Representations
Kabir, S., Li, L., & Zhang, T. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642111 · Cited by 8
Metadata
- Authors
- Papakyriakopoulos, O., Hegelich, S., Serrano, J. C. M., & Marco, F.
- Venue
- Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency
- Publisher
- ACM
- Published
- 2020-01-27
- Pages
- 446-457
- OpenAlex
- W3013854004
- Cited by
- 88
- References
- 17
- FWCI
- 17.23
- Type
- conference paper
- Language
- en
- Open access
- gold
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: Bias in word embeddings. https://app.cochat.ai/papers/10.1145/3351095.3372843
- The paper
- Papakyriakopoulos, O., Hegelich, S., Serrano, J. C. M., & Marco, F. (2020). Bias in word embeddings. Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency. https://doi.org/10.1145/3351095.3372843
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.