Quantifying Gender Bias in Different Corpora
Open accessThe 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.
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 6×
“Specifically, we measure and analyze the gender bias in word embeddings using Bidirectional Encoder Representation of Transformers (BERT) and the direct gender bias calculation proposed by Bolukbasi et al. in their paper “Man is to computer programmer as woman is to homemaker?”
BackgroundMethodInfluentialMan 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
Amazon Scraps Secret AI Recruiting Tool that Showed Bias against Women *
Dastin, J. (2022) · Ethics of Data and Analytics · doi:10.1201/9781003278290-44 · Cited by 1,165
Cited by
Underspecification Presents Challenges for Credibility in Modern Machine Learning
D'Amour, A., Heller, K., Moldovan, D., Adlam, B., Alipanahi, B., Beutel, A., Chen, C., Deaton, J., Eisenstein, J., Hoffman, M. D., et al. (2020) · arXiv · doi:10.48550/arxiv.2011.03395 · Cited by 398
“Finally, we note that the particular axes along which we observe sensitivity depends on the dataset used to train the embeddings, and could vary on embeddings trained on other corpora (Babaeianjelodar et al., 2020).”
BackgroundHutchinson, B., Smart, A., Hanna, A., Denton, R., Greer, C., Kjartansson, O., Barnes, P., & Mitchell, M. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445918 · Cited by 279
SqueezeBERT: What can computer vision teach NLP about efficient neural networks?
Iandola, F., Shaw, A., Krishna, R., & Keutzer, K. (2020) · Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing · doi:10.18653/v1/2020.sustainlp-1.17 · Cited by 114
Garrido-Muñoz, I., Montejo-Ráez, A., Martínez-Santiago, F., & Ureña-López, L. A. (2021) · Applied Sciences · doi:10.3390/app11073184 · Cited by 123
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
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
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.