The Role of Protected Class Word Lists in Bias Identification of Contextualized Word Representations
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
Systemic bias in word embeddings has been widely reported and studied, and efforts made to debias them; however, new contextualized embeddings such as ELMo and BERT are only now being similarly studied.Standard debiasing methods require large, heterogeneous lists of target words to identify the "bias subspace".We show that using new contextualized word embeddings in conceptor debiasing allows us to more accurately debias word embeddings by breaking target word lists into more homogeneous subsets and then combining ("Or'ing") the debiasing conceptors of the different subsets.
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. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
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
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983
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 5×
“…BERT have bias similar (Wang et al., 2019; May et al., 2019; Kurita et al., 2019) to the well documented bias in traditional word embedding methods (Bolukbasi et al., 2016; Bha-tia, 2017; Caliskan et al., 2017; Nikhil Garg and Zou, 2018; Kiritchenko and Mohammad, 2018; Rudinger et al., 2018; Zhang…”
BackgroundMethodInfluentialMitigating Unwanted Biases with Adversarial Learning
Zhang, B. H., Lemoine, B., & Mitchell, M. (2018) · Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3278721.3278779 · Cited by 1,387 · cited 1×
“…(Bolukbasi et al., 2016; Bha-tia, 2017; Caliskan et al., 2017; Nikhil Garg and Zou, 2018; Kiritchenko and Mohammad, 2018; Rudinger et al., 2018; Zhang et al., 2018), and this could cause bias in NLP pipelines used for high stakes downstream tasks such as resume selection or bail setting…”
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 2×
“…et al., 2019) to the well documented bias in traditional word embedding methods (Bolukbasi et al., 2016; Bha-tia, 2017; Caliskan et al., 2017; Nikhil Garg and Zou, 2018; Kiritchenko and Mohammad, 2018; Rudinger et al., 2018; Zhang et al., 2018), and this could cause bias in NLP pipelines…”
BackgroundMen Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
Zhao, J., Wang, T., Yatskar, M., Ordonez, V., & Chang, K.-W. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1323 · Cited by 829 · cited 1×
“…age and gender (Hovy, 2015; Dixon et al., 2018), to over-amplification of demographic differences in language generation (Yatskar et al., 2016; Zhao et al., 2017), to diverging implicit associations be-tween words or concepts within embeddings or language models (Bolukbasi et al., 2016;…”
BackgroundMeasuring 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 1×
“Demographic biases manifest in many ways, from disparities in tagging and classification accuracy depending on author age and gender (Hovy, 2015; Dixon et al., 2018), to over-amplification of demographic differences in language generation (Yatskar et al., 2016; Zhao et al., 2017), to diverging…”
BackgroundOn Measuring Social Biases in Sentence Encoders
May, C., Wang, A., Bordia, S., Bowman, S. R., & Rudinger, R. (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/n19-1063 · Cited by 461 · cited 2×
“However, May et al. (2019) found that bias in BERT may be more difficult to identify, but Kurita et al. (2019) did indeed find bias in BERT.”
BackgroundMethodGonen, H., & Goldberg, Y. (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/n19-1061 · Cited by 454 · cited 1×
“In fact recent work by Gonen and Goldberg (2019) has pointed out that most “debiasing” methods are simply mitigating bias and thus end task methods will potentially be able to undo this mitigation.”
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
Towards trustworthy LLMs: a review on debiasing and dehallucinating in large language models
Lin, Z., Guan, S., Zhang, W., Zhang, H., Li, Y., & Zhang, H. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10896-y · Cited by 141
Czarnowska, P., Vyas, Y., & Shah, K. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00425 · Cited by 72
“…line of research measures bias present in sentence or word representations (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.,…”
BackgroundPerturbation augmentation for fairer NLP
Qian, R., Ross, C., Fernandes, J., Smith, E. M., Kiela, D., & Williams, A. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.646 · Cited by 69
Delobelle, P., Tokpo, E., Calders, T., & Berendt, B. (2022) · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2022.naacl-main.122 · Cited by 57
Metadata
- Authors
- Sedoc, J., & Ungar, L.
- Venue
- Proceedings of the First Workshop on Gender Bias in Natural Language Processing
- Published
- 2019
- OpenAlex
- W2972697496
- Cited by
- 16
- References
- 17
- FWCI
- 2.46
- 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: The Role of Protected Class Word Lists in Bias Identification of Contextualized Word Representations. https://app.cochat.ai/papers/10.18653/v1/w19-3808
- The paper
- Sedoc, J., & Ungar, L. (2019). The Role of Protected Class Word Lists in Bias Identification of Contextualized Word Representations. Proceedings of the First Workshop on Gender Bias in Natural Language Processing. https://doi.org/10.18653/v1/w19-3808
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.