CoChat

Quantifying Gender Bias in Different Corpora

Open access
Babaeianjelodar, Marzieh, Lorenz, Stephen, Gordon, Josh, Matthews, Jeanna, Freitag, Evan · 2020 · Companion Proceedings of the Web Conference 2020
Cited by 43

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Abstract

Word embedding models have been shown to be effective in performing a wide variety of Natural Language Processing (NLP) tasks such as identifying audiences for web advertisements, parsing resumés to select promising job candidates, and translating documents from one language to another. However, it has been demonstrated that NLP systems learn gender bias from the corpora of documents on which they are trained. It is increasingly common for pre-trained models to be used as a starting point for building applications in a wide range of areas including critical decision making applications. It is also very easy to use a pre-trained model as the basis for a new application without careful consideration of the original nature of the training set. In this paper, we quantify the degree to which gender bias differs with the corpora used for training. We look especially at the impact of starting with a pre-trained model and fine-tuning with additional data. Specifically, we calculate a measure of direct gender bias on several pre-trained models including BERT’s Wikipedia and Book corpus models as well as on several fine-tuned General Language Understanding Evaluation (GLUE) benchmarks. In addition, we evaluate the bias from several more extreme corpora including the Jigsaw identity toxic dataset that includes toxic speech biased against race, gender, religion, and disability and the RtGender dataset that includes speech specifically labelled by gender. Our results reveal that the direct gender bias of the Jigsaw toxic identity dataset is surprisingly close to that of the base pre-trained Google model, but the RtGender dataset has significantly higher direct gender bias than the base model. When the bias learned by an NLP system can vary significantly with the corpora used for training, it becomes important to consider and report these details, especially for use in critical decision-making 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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3366424.3383559

Cites

3 of 3 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 3 references

Cited by

See all 43

Metadata

Authors
Babaeianjelodar, M., Lorenz, S., Gordon, J., Matthews, J., & Freitag, E.
Venue
Companion Proceedings of the Web Conference 2020
Publisher
ACM
Published
2020-04-20
Pages
752-759
OpenAlex
W3023547440
Cited by
43
References
3
FWCI
9.69
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: Quantifying Gender Bias in Different Corpora. https://app.cochat.ai/papers/10.1145/3366424.3383559
The paper
Babaeianjelodar, M., Lorenz, S., Gordon, J., Matthews, J., & Freitag, E. (2020). Quantifying Gender Bias in Different Corpora. Companion Proceedings of the Web Conference 2020. https://doi.org/10.1145/3366424.3383559

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.