---
title: "Debiasing Pre-trained Contextualised — Kaneko 2021"
description: "Contextualised encoders such as BERT absorb social biases, yet removing them has received far less attention than for static word vectors."
authors: ["Masahiro Kaneko", "Danushka Bollegala"]
year: 2021
venue: "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume"
source: "https://aclanthology.org/2021.eacl-main.107/"
doi: "10.18653/v1/2021.eacl-main.107"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/kaneko-2021-debiasing-pre-trained-contextualised-embeddings/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/kaneko-2021-debiasing-pre-trained-contextualised-embeddings/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2021](https://md.research.elamur.ai/free/en/papers/2021/page/2/) / Debiasing Pre-trained Contextualised Embeddings

# Debiasing Pre-trained Contextualised Embeddings

**Authors:** [Masahiro Kaneko](https://md.research.elamur.ai/free/en/authors/masahiro-kaneko/), [Danushka Bollegala](https://md.research.elamur.ai/free/en/authors/danushka-bollegala/) · **Year:** 2021 · **Venue:** Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2021.eacl-main.107/) · [PDF](https://aclanthology.org/2021.eacl-main.107.pdf) · [DOI 10.18653/v1/2021.eacl-main.107](https://doi.org/10.18653/v1/2021.eacl-main.107) · [OpenAlex](https://openalex.org/W3155655882)

**Citations:** 87 citations (openalex-snapshot · 2026-10-14) · [87](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
Contextualised encoders such as BERT absorb social biases, yet removing them has received far less attention than for static word vectors. Projection-based fixes do not transfer easily: bias is spread across many interacting parameters and depends on context, and retraining on gender-swapped corpora is costly. Kaneko and Bollegala propose an architecture-agnostic fine-tuning procedure that keeps the gender meaning of gender-definitional words while removing stereotypical gender associations, without pre-training from scratch. It works on token-level or sentence-level representations and can target selected layers or every layer. Using gender bias as the case study, they apply it to BERT, RoBERTa, ALBERT, DistilBERT and ELECTRA. Bias is measured with SEAT and the MNLI-based bias test of Dev et al. (2020). Retained usefulness is checked on GLUE-style downstream tasks. The best setting debiases all tokens in all layers. It reduces bias while largely keeping downstream accuracy, though how well this trade-off holds varies by model. The method matters because it offers a cheap debiasing step that fits the common practice of sharing and fine-tuning pre-trained models.

## Key points
- The authors test three token-level variants (all-token, first-token, last-token) plus a sentence-level option. The all-token approach applied to every layer is consistently least biased on SEAT 6, 7 and 8. Debiasing only some layers is insufficient, even for the shallow DistilBERT.
- They compare against Dev et al. (2020), who project out the gender direction only in Layer 1 of BERT-large. The proposed method scores better on the NN and T:0.7 bias measures, and its MNLI-m/MNLI-mm entailment accuracy stays close to the original model's.
- Downstream checks cover:
  - sentiment classification
  - paraphrase detection
  - semantic textual similarity
  - NLI
  - Winograd schema (WNLI)
- WNLI gains are judged insignificant because WNLI has only 146 test instances.
- Plots of gender scores for stereotype words show different behaviour by model:
  - BERT, DistilBERT and ELECTRA keep their original distribution shape while moving towards zero.
  - ALBERT over-debiases, collapsing these words near zero.
  - RoBERTa under-debiases.
- Code and debiased embeddings are released at github.com/kanekomasahiro/context-debias.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

## Cited by

Cited by

87 papers of our library cite it (of the 140884 whose bibliographies we read); 5 of them have a page here, 82 not yet.

- [Bias and Fairness in Large Language Models: A Survey](https://md.research.elamur.ai/free/en/papers/gallegos-2023-bias-fairness-large-language-models/)
- [Auto-Debias: Debiasing Masked Language Models with Automated Biased Prompts](https://md.research.elamur.ai/free/en/papers/guo-2022-auto-debias-debiasing-masked-language/)
- [Sustainable Modular Debiasing of Language Models](https://md.research.elamur.ai/free/en/papers/lauscher-2021-sustainable-modular-debiasing-language-models/)
- [An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models](https://md.research.elamur.ai/free/en/papers/meade-2022-empirical-survey-effectiveness-debiasing-techniques/)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://md.research.elamur.ai/free/en/papers/schick-2021-self-diagnosis-self-debiasing-proposal/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{kaneko2021debiasing,
  title = {{Debiasing Pre-trained Contextualised Embeddings}},
  author = {Kaneko, Masahiro and Bollegala, Danushka},
  booktitle = {Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume},
  year = {2021},
  doi = {10.18653/v1/2021.eacl-main.107},
  url = {https://doi.org/10.18653/v1/2021.eacl-main.107}
}
```

- [← previous DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://md.research.elamur.ai/free/en/papers/he-2021-debertav3-improving-deberta-using-electra/)
- [next → Deciphering Undersegmented Ancient Scripts Using Phonetic Prior](https://md.research.elamur.ai/free/en/papers/tacl-2021-luo-deciphering-undersegmented-ancient-scripts-phonetic/)
- [↑ back to papers of 2021](https://md.research.elamur.ai/free/en/papers/2021/page/2/)

## References

45 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Roy Bar-Haim, Ido Dagan, Bill Dolan, Lisa Ferro, and Danilo Giampiccolo. 2006. The second pascal recognising textual entailment challenge. Proceedings of the Second PASCAL Challenges Workshop on Recognising Textual Entailment. [find](https://scholar.google.com/scholar?q=Roy+Bar%2DHaim%2C+Ido+Dagan%2C+Bill+Dolan%2C+Lisa+Ferro%2C+and+Danilo+Giampiccolo%2E+2006%2E+The+second+pascal+recognising+textual+entailment+challenge%2E+Proceedings+of+the+Second+PASCAL+Challenges+Workshop+on+Recog)
2. Luisa Bentivogli, Ido Dagan, Hoa Trang Dang, Danilo Giampiccolo, and Bernardo Magnini. 2009. The fifth pascal recognizing textual entailment challenge. In In Proc Text Analysis Conference (TAC’09. [find](https://scholar.google.com/scholar?q=Luisa+Bentivogli%2C+Ido+Dagan%2C+Hoa+Trang+Dang%2C+Danilo+Giampiccolo%2C+and+Bernardo+Magnini%2E+2009%2E+The+fifth+pascal+recognizing+textual+entailment+challenge%2E+In+In+Proc+Text+Analysis+Conference+%28TAC%E2%80%9909%2E)
3. Tolga Bolukbasi, Kai-Wei Chang, James Y. Zou, Venkatesh Saligrama, and Adam Kalai. 2016. Man is to computer programmer as woman is to homemaker? debiasing word embeddings. In NIPS. [find](https://scholar.google.com/scholar?q=Tolga+Bolukbasi%2C+Kai%2DWei+Chang%2C+James+Y%2E+Zou%2C+Venkatesh+Saligrama%2C+and+Adam+Kalai%2E+2016%2E+Man+is+to+computer+programmer+as+woman+is+to+homemaker%3F+debiasing+word+embeddings%2E+In+NIPS%2E) [our card](https://md.research.elamur.ai/free/en/papers/bolukbasi-2016-man-computer-programmer-woman-homemaker/)
4. Rishi Bommasani, Kelly Davis, and Claire Cardie. 2020. Interpreting Pretrained Contextualized Representations via Reductions to Static Embeddings. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4758– 4781, Online. Association for Computational Lingu… [find](https://scholar.google.com/scholar?q=Rishi+Bommasani%2C+Kelly+Davis%2C+and+Claire+Cardie%2E+2020%2E+Interpreting+Pretrained+Contextualized+Representations+via+Reductions+to+Static+Embeddings%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+Asso) [our card](https://md.research.elamur.ai/free/en/papers/bommasani-2020-interpreting-pretrained-contextualized-representations-reductions/)
5. Shikha Bordia and Samuel R. Bowman. 2019. Identifying and reducing gender bias in word-level language models. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 7–15, Minneapolis, Minnesota. Associati… [find](https://scholar.google.com/scholar?q=Shikha+Bordia+and+Samuel+R%2E+Bowman%2E+2019%2E+Identifying+and+reducing+gender+bias+in+word%2Dlevel+language+models%2E+In+Proceedings+of+the+2019+Conference+of+the+North+American+Chapter+of+the+Association+for) [our card](https://md.research.elamur.ai/free/en/papers/bordia-2019-identifying-reducing-gender-bias-word/)
6. Aylin Caliskan, Joanna J Bryson, and Arvind Narayanan. 2017. Semantics derived automatically from language corpora contain human-like biases. Science, 356:183–186. [find](https://scholar.google.com/scholar?q=Aylin+Caliskan%2C+Joanna+J+Bryson%2C+and+Arvind+Narayanan%2E+2017%2E+Semantics+derived+automatically+from+language+corpora+contain+human%2Dlike+biases%2E+Science%2C+356%3A183%E2%80%93186%2E)
7. Daniel Cer, Mona Diab, Eneko Agirre, Iñigo Lopez-Gazpio, and Lucia Specia. 2017. SemEval-2017 task 1: Semantic textual similarity multilingual and crosslingual focused evaluation. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 1–14, Vancouver, Canada.… [find](https://scholar.google.com/scholar?q=Daniel+Cer%2C+Mona+Diab%2C+Eneko+Agirre%2C+In%CC%83igo+Lopez%2DGazpio%2C+and+Lucia+Specia%2E+2017%2E+SemEval%2D2017+task+1%3A+Semantic+textual+similarity+multilingual+and+crosslingual+focused+evaluation%2E+In+Proceedings+of+t)
8. K. Clark, Minh-Thang Luong, Quoc V. Le, and Christopher D. Manning. 2020. Electra: Pre-training text encoders as discriminators rather than generators. ArXiv, abs/2003.10555. [find](https://scholar.google.com/scholar?q=K%2E+Clark%2C+Minh%2DThang+Luong%2C+Quoc+V%2E+Le%2C+and+Christopher+D%2E+Manning%2E+2020%2E+Electra%3A+Pre%2Dtraining+text+encoders+as+discriminators+rather+than+generators%2E+ArXiv%2C+abs%2F2003%2E10555%2E)
9. Ido Dagan, Oren Glickman, and Bernardo Magnini. 2005. The pascal recognising textual entailment challenge. In Proceedings of the First International Conference on Machine Learning Challenges: Evaluating Predictive Uncertainty Visual Object Classification, and Recognizing Textual Entailment, MLCW’05,… [find](https://scholar.google.com/scholar?q=Ido+Dagan%2C+Oren+Glickman%2C+and+Bernardo+Magnini%2E+2005%2E+The+pascal+recognising+textual+entailment+challenge%2E+In+Proceedings+of+the+First+International+Conference+on+Machine+Learning+Challenges%3A+Evaluati)
10. Sunipa Dev, Tao Li, Jeff Phillips, and Vivek Srikumar. 2020. On Measuring and Mitigating Biased Inferences of Word Embeddings. In AAAI. [find](https://scholar.google.com/scholar?q=Sunipa+Dev%2C+Tao+Li%2C+Jeff+Phillips%2C+and+Vivek+Srikumar%2E+2020%2E+On+Measuring+and+Mitigating+Biased+Inferences+of+Word+Embeddings%2E+In+AAAI%2E)
11. Sunipa Dev and Jeff M. Phillips. 2019. Attenuating bias in word vectors. In The 22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019, 16-18 April 2019, Naha, Okinawa, Japan, volume 89 of Proceedings of Machine Learning Research, pages 879–887. PMLR. [find](https://scholar.google.com/scholar?q=Sunipa+Dev+and+Jeff+M%2E+Phillips%2E+2019%2E+Attenuating+bias+in+word+vectors%2E+In+The+22nd+International+Conference+on+Artificial+Intelligence+and+Statistics%2C+AISTATS+2019%2C+16%2D18+April+2019%2C+Naha%2C+Okinawa%2C+)
12. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,… [find](https://scholar.google.com/scholar?q=Jacob+Devlin%2C+Ming%2DWei+Chang%2C+Kenton+Lee%2C+and+Kristina+Toutanova%2E+2019%2E+BERT%3A+Pre%2Dtraining+of+deep+bidirectional+transformers+for+language+understanding%2E+In+Proceedings+of+the+2019+Conference+of+the+N)
13. Simon De Deyne, Danielle J. Navarro, Amy Perfors, Marc Brysbaert, and Gert Storms. 2019. The “small world of words” english word association norms for over 12,000 cue words. Behavior Research Methods, 51:987–1006. [find](https://scholar.google.com/scholar?q=Simon+De+Deyne%2C+Danielle+J%2E+Navarro%2C+Amy+Perfors%2C+Marc+Brysbaert%2C+and+Gert+Storms%2E+2019%2E+The+%E2%80%9Csmall+world+of+words%E2%80%9D+english+word+association+norms+for+over+12%2C000+cue+words%2E+Behavior+Research+Methods%2C)
14. William B. Dolan and Chris Brockett. 2005. Automatically constructing a corpus of sentential paraphrases. In Proceedings of the Third International Workshop on Paraphrasing (IWP2005). [find](https://scholar.google.com/scholar?q=William+B%2E+Dolan+and+Chris+Brockett%2E+2005%2E+Automatically+constructing+a+corpus+of+sentential+paraphrases%2E+In+Proceedings+of+the+Third+International+Workshop+on+Paraphrasing+%28IWP2005%29%2E) [our card](https://md.research.elamur.ai/free/en/papers/dolan-2005-automatically-constructing-corpus-sentential-paraphrases/)
15. Yupei Du, Yuanbin Wu, and Man Lan. 2019. Exploring human gender stereotypes with word association test. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6133– 6143… [find](https://scholar.google.com/scholar?q=Yupei+Du%2C+Yuanbin+Wu%2C+and+Man+Lan%2E+2019%2E+Exploring+human+gender+stereotypes+with+word+association+test%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+in+Natural+Language+Processing+and+th)
16. Yanai Elazar and Yoav Goldberg. 2018. Adversarial Removal of Demographic Attributes from Text Data. In Proc. of EMNLP. [find](https://scholar.google.com/scholar?q=Yanai+Elazar+and+Yoav+Goldberg%2E+2018%2E+Adversarial+Removal+of+Demographic+Attributes+from+Text+Data%2E+In+Proc%2E+of+EMNLP%2E) [our card](https://md.research.elamur.ai/free/en/papers/elazar-2018-adversarial-removal-demographic-attributes-text/)
17. Danilo Giampiccolo, Bernardo Magnini, Ido Dagan, and Bill Dolan. 2007. The Third PASCAL Recognizing Textual Entailment Challenge, pages 1–9. Association for Computational Linguistics, USA. [find](https://scholar.google.com/scholar?q=Danilo+Giampiccolo%2C+Bernardo+Magnini%2C+Ido+Dagan%2C+and+Bill+Dolan%2E+2007%2E+The+Third+PASCAL+Recognizing+Textual+Entailment+Challenge%2C+pages+1%E2%80%939%2E+Association+for+Computational+Linguistics%2C+USA%2E)
18. Hila Gonen and Yoav Goldberg. 2019. Lipstick on a pig: Debiasing methods cover up systematic gender biases in word embeddings but do not remove them. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol… [find](https://scholar.google.com/scholar?q=Hila+Gonen+and+Yoav+Goldberg%2E+2019%2E+Lipstick+on+a+pig%3A+Debiasing+methods+cover+up+systematic+gender+biases+in+word+embeddings+but+do+not+remove+them%2E+In+Proceedings+of+the+2019+Conference+of+the+North) [our card](https://md.research.elamur.ai/free/en/papers/gonen-2019-lipstick-pig-debiasing-methods-cover/)
19. Proceedings of the Thirteenth International Conference on Principles of Knowledge Representation and Reasoning, KR’12, pages 552–561. AAAI Press. [find](https://scholar.google.com/scholar?q=Proceedings+of+the+Thirteenth+International+Conference+on+Principles+of+Knowledge+Representation+and+Reasoning%2C+KR%E2%80%9912%2C+pages+552%E2%80%93561%2E+AAAI+Press%2E)
20. Yitong Li, Timothy Baldwin, and Trevor Cohn. 2018. Towards robust and privacy-preserving text representations. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 25–30. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yitong+Li%2C+Timothy+Baldwin%2C+and+Trevor+Cohn%2E+2018%2E+Towards+robust+and+privacy%2Dpreserving+text+representations%2E+In+Proceedings+of+the+56th+Annual+Meeting+of+the+Association+for+Computational+Linguistic) [our card](https://md.research.elamur.ai/free/en/papers/li-2018-robust-privacy-preserving-text-representations/)
21. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692. [find](https://scholar.google.com/scholar?q=Yinhan+Liu%2C+Myle+Ott%2C+Naman+Goyal%2C+Jingfei+Du%2C+Mandar+Joshi%2C+Danqi+Chen%2C+Omer+Levy%2C+Mike+Lewis%2C+Luke+Zettlemoyer%2C+and+Veselin+Stoyanov%2E+2019%2E+Roberta%3A+A+robustly+optimized+bert+pretraining+approach%2E+a)
22. Rowan Hall Maudslay, Hila Gonen, Ryan Cotterell, and Simone Teufel. 2019. It’s all in the name: Mitigating gender bias with name-based counterfactual data substitution. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferenc… [find](https://scholar.google.com/scholar?q=Rowan+Hall+Maudslay%2C+Hila+Gonen%2C+Ryan+Cotterell%2C+and+Simone+Teufel%2E+2019%2E+It%E2%80%99s+all+in+the+name%3A+Mitigating+gender+bias+with+name%2Dbased+counterfactual+data+substitution%2E+In+Proceedings+of+the+2019+Conf)
23. Chandler May, Alex Wang, Shikha Bordia, Samuel R. Bowman, and Rachel Rudinger. 2019. On measuring social biases in sentence encoders. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and… [find](https://scholar.google.com/scholar?q=Chandler+May%2C+Alex+Wang%2C+Shikha+Bordia%2C+Samuel+R%2E+Bowman%2C+and+Rachel+Rudinger%2E+2019%2E+On+measuring+social+biases+in+sentence+encoders%2E+In+Proceedings+of+the+2019+Conference+of+the+North+American+Chapte) [our card](https://md.research.elamur.ai/free/en/papers/may-2019-measuring-social-biases-sentence-encoders/)
24. Masahiro Kaneko and Danushka Bollegala. 2019. Gender-preserving debiasing for pre-trained word embeddings. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1641–1650, Florence, Italy. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Masahiro+Kaneko+and+Danushka+Bollegala%2E+2019%2E+Gender%2Dpreserving+debiasing+for+pre%2Dtrained+word+embeddings%2E+In+Proceedings+of+the+57th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+p)
25. Tomas Mikolov, Kai Chen, and Jeffrey Dean. 2013. Efficient estimation of word representation in vector space. In ICLR. [find](https://scholar.google.com/scholar?q=Tomas+Mikolov%2C+Kai+Chen%2C+and+Jeffrey+Dean%2E+2013%2E+Efficient+estimation+of+word+representation+in+vector+space%2E+In+ICLR%2E)
26. Masahiro Kaneko and Danushka Bollegala. 2020. Autoencoding improves pre-trained word embeddings. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1699–1713, Barcelona, Spain (Online). International Committee on Computational Linguistics. [find](https://scholar.google.com/scholar?q=Masahiro+Kaneko+and+Danushka+Bollegala%2E+2020%2E+Autoencoding+improves+pre%2Dtrained+word+embeddings%2E+In+Proceedings+of+the+28th+International+Conference+on+Computational+Linguistics%2C+pages+1699%E2%80%931713%2C+Barc)
27. Saket Karve, Lyle Ungar, and João Sedoc. 2019. Conceptor debiasing of word representations evaluated on WEAT. In Proceedings of the First Workshop on Gender Bias in Natural Language Processing, pages 40–48, Florence, Italy. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Saket+Karve%2C+Lyle+Ungar%2C+and+Joa%CC%83o+Sedoc%2E+2019%2E+Conceptor+debiasing+of+word+representations+evaluated+on+WEAT%2E+In+Proceedings+of+the+First+Workshop+on+Gender+Bias+in+Natural+Language+Processing%2C+pages)
28. Keita Kurita, Nidhi Vyas, Ayush Pareek, Alan W Black, and Yulia Tsvetkov. 2019. Measuring bias in contextualized word representations. In Proceedings of the First Workshop on Gender Bias in Natural Language Processing, pages 166–172, Florence, Italy. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Keita+Kurita%2C+Nidhi+Vyas%2C+Ayush+Pareek%2C+Alan+W+Black%2C+and+Yulia+Tsvetkov%2E+2019%2E+Measuring+bias+in+contextualized+word+representations%2E+In+Proceedings+of+the+First+Workshop+on+Gender+Bias+in+Natural+La) [our card](https://md.research.elamur.ai/free/en/papers/kurita-2019-measuring-bias-contextualized-word-representations/)
29. Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. Albert: A lite bert for self-supervised learning of language representations. ArXiv, abs/1909.11942. [find](https://scholar.google.com/scholar?q=Zhenzhong+Lan%2C+Mingda+Chen%2C+Sebastian+Goodman%2C+Kevin+Gimpel%2C+Piyush+Sharma%2C+and+Radu+Soricut%2E+2020%2E+Albert%3A+A+lite+bert+for+self%2Dsupervised+learning+of+language+representations%2E+ArXiv%2C+abs%2F1909%2E11942%2E)
30. Hector J. Levesque, Ernest Davis, and Leora Morgenstern. 2012. The winograd schema challenge. In Moin Nadeem, Anna Bethke, and Siva Reddy. 2020. StereoSet: Measuring stereotypical bias in pre-trained language models. [find](https://scholar.google.com/scholar?q=Hector+J%2E+Levesque%2C+Ernest+Davis%2C+and+Leora+Morgenstern%2E+2012%2E+The+winograd+schema+challenge%2E+In+Moin+Nadeem%2C+Anna+Bethke%2C+and+Siva+Reddy%2E+2020%2E+StereoSet%3A+Measuring+stereotypical+bias+in+pre%2Dtrained+)
31. Nikita Nangia, Clara Vania, Rasika Bhalerao, and Samuel R. Bowman. 2020. CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models. In Proc. of EMNLP. [find](https://scholar.google.com/scholar?q=Nikita+Nangia%2C+Clara+Vania%2C+Rasika+Bhalerao%2C+and+Samuel+R%2E+Bowman%2E+2020%2E+CrowS%2DPairs%3A+A+Challenge+Dataset+for+Measuring+Social+Biases+in+Masked+Language+Models%2E+In+Proc%2E+of+EMNLP%2E) [our card](https://md.research.elamur.ai/free/en/papers/nangia-2020-crows-pairs-challenge-dataset-measuring/)
32. Jeffery Pennington, Richard Socher, and Christopher D. Manning. 2014. Glove: global vectors for word representation. In EMNLP, pages 1532–1543. [find](https://scholar.google.com/scholar?q=Jeffery+Pennington%2C+Richard+Socher%2C+and+Christopher+D%2E+Manning%2E+2014%2E+Glove%3A+global+vectors+for+word+representation%2E+In+EMNLP%2C+pages+1532%E2%80%931543%2E)
33. Shauli Ravfogel, Yanai Elazar, Hila Gonen, Michael Twiton, and Yoav Goldberg. 2020. Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection. In Proc. of ACL. [find](https://scholar.google.com/scholar?q=Shauli+Ravfogel%2C+Yanai+Elazar%2C+Hila+Gonen%2C+Michael+Twiton%2C+and+Yoav+Goldberg%2E+2020%2E+Null+It+Out%3A+Guarding+Protected+Attributes+by+Iterative+Nullspace+Projection%2E+In+Proc%2E+of+ACL%2E) [our card](https://md.research.elamur.ai/free/en/papers/ravfogel-2020-null-it-out-guarding-protected/)
34. Rachel Rudinger, Jason Naradowsky, Brian Leonard, and Benjamin Van Durme. 2018. Gender bias in coreference resolution. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 8–1… [find](https://scholar.google.com/scholar?q=Rachel+Rudinger%2C+Jason+Naradowsky%2C+Brian+Leonard%2C+and+Benjamin+Van+Durme%2E+2018%2E+Gender+bias+in+coreference+resolution%2E+In+Proceedings+of+the+2018+Conference+of+the+North+American+Chapter+of+the+Associ) [our card](https://md.research.elamur.ai/free/en/papers/rudinger-2018-gender-bias-coreference-resolution/)
35. Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. ArXiv, abs/1910.01108. [find](https://scholar.google.com/scholar?q=Victor+Sanh%2C+Lysandre+Debut%2C+Julien+Chaumond%2C+and+Thomas+Wolf%2E+2019%2E+Distilbert%2C+a+distilled+version+of+bert%3A+smaller%2C+faster%2C+cheaper+and+lighter%2E+ArXiv%2C+abs%2F1910%2E01108%2E)
36. Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Ng, and Christopher Potts. 2013. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1631–… [find](https://scholar.google.com/scholar?q=Richard+Socher%2C+Alex+Perelygin%2C+Jean+Wu%2C+Jason+Chuang%2C+Christopher+D%2E+Manning%2C+Andrew+Ng%2C+and+Christopher+Potts%2E+2013%2E+Recursive+deep+models+for+semantic+compositionality+over+a+sentiment+treebank%2E+In)
37. Learning with local and global consistency. NIPS. In Ran Zmigrod, Sebastian J. Mielke, Hanna Wallach, and Ryan Cotterell. 2019. Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology. In Proc. of ACL. [find](https://scholar.google.com/scholar?q=Learning+with+local+and+global+consistency%2E+NIPS%2E+In+Ran+Zmigrod%2C+Sebastian+J%2E+Mielke%2C+Hanna+Wallach%2C+and+Ryan+Cotterell%2E+2019%2E+Counterfactual+Data+Augmentation+for+Mitigating+Gender+Stereotypes+in+La) [our card](https://md.research.elamur.ai/free/en/papers/zmigrod-2019-counterfactual-data-augmentation-mitigating-gender/)
38. Yi Chern Tan and L. Elisa Celis. 2019. Assessing social and intersectional biases in contextualized word representations. In Advances in Neural Information Processing Systems 32, pages 13230–13241. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Yi+Chern+Tan+and+L%2E+Elisa+Celis%2E+2019%2E+Assessing+social+and+intersectional+biases+in+contextualized+word+representations%2E+In+Advances+in+Neural+Information+Processing+Systems+32%2C+pages+13230%E2%80%9313241%2E+Cu)
39. Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman. 2018. GLUE: A multi-task benchmark and analysis platform for natural language understanding. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 353–355,… [find](https://scholar.google.com/scholar?q=Alex+Wang%2C+Amanpreet+Singh%2C+Julian+Michael%2C+Felix+Hill%2C+Omer+Levy%2C+and+Samuel+Bowman%2E+2018%2E+GLUE%3A+A+multi%2Dtask+benchmark+and+analysis+platform+for+natural+language+understanding%2E+In+Proceedings+of+the) [our card](https://md.research.elamur.ai/free/en/papers/wang-2018-glue-multi-task-benchmark-analysis/)
40. Adina Williams, Nikita Nangia, and Samuel Bowman. 2018. A broad-coverage challenge corpus for sentence understanding through inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Pa… [find](https://scholar.google.com/scholar?q=Adina+Williams%2C+Nikita+Nangia%2C+and+Samuel+Bowman%2E+2018%2E+A+broad%2Dcoverage+challenge+corpus+for+sentence+understanding+through+inference%2E+In+Proceedings+of+the+2018+Conference+of+the+North+American+Chap)
41. Qizhe Xie, Zihang Dai, Yulun Du, Eduard Hovy, and Graham Neubig. 2017. Controllable invariance through adversarial feature learning. In Proc. of NIPS. [find](https://scholar.google.com/scholar?q=Qizhe+Xie%2C+Zihang+Dai%2C+Yulun+Du%2C+Eduard+Hovy%2C+and+Graham+Neubig%2E+2017%2E+Controllable+invariance+through+adversarial+feature+learning%2E+In+Proc%2E+of+NIPS%2E)
42. Jieyu Zhao, Tianlu Wang, Mark Yatskar, Ryan Cotterell, Vicente Ordonez, and Kai-Wei Chang. 2019. Gender bias in contextualized word embeddings. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1… [find](https://scholar.google.com/scholar?q=Jieyu+Zhao%2C+Tianlu+Wang%2C+Mark+Yatskar%2C+Ryan+Cotterell%2C+Vicente+Ordonez%2C+and+Kai%2DWei+Chang%2E+2019%2E+Gender+bias+in+contextualized+word+embeddings%2E+In+Proceedings+of+the+2019+Conference+of+the+North+Ameri) [our card](https://md.research.elamur.ai/free/en/papers/zhao-2019-gender-bias-contextualized-word-embeddings/)
43. Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, and Kai-Wei Chang. 2018a. Gender bias in coreference resolution: Evaluation and debiasing methods. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies… [find](https://scholar.google.com/scholar?q=Jieyu+Zhao%2C+Tianlu+Wang%2C+Mark+Yatskar%2C+Vicente+Ordonez%2C+and+Kai%2DWei+Chang%2E+2018a%2E+Gender+bias+in+coreference+resolution%3A+Evaluation+and+debiasing+methods%2E+In+Proceedings+of+the+2018+Conference+of+the+) [our card](https://md.research.elamur.ai/free/en/papers/zhao-2018-gender-bias-coreference-resolution-evaluation/)
44. Jieyu Zhao, Yichao Zhou, Zeyu Li, Wei Wang, and Kai-Wei Chang. 2018b. Learning Gender-Neutral Word Embeddings. In Proc. of EMNLP, pages 4847– 4853. [find](https://scholar.google.com/scholar?q=Jieyu+Zhao%2C+Yichao+Zhou%2C+Zeyu+Li%2C+Wei+Wang%2C+and+Kai%2DWei+Chang%2E+2018b%2E+Learning+Gender%2DNeutral+Word+Embeddings%2E+In+Proc%2E+of+EMNLP%2C+pages+4847%E2%80%93+4853%2E) [our card](https://md.research.elamur.ai/free/en/papers/zhao-2018-learning-gender-neutral-word-embeddings/)
45. Dengyong Zhou, Olivier Bousquet, Thomas Navin Lal, Jason Weston, and Bernhard Schölkopf. 2003. [find](https://scholar.google.com/scholar?q=Dengyong+Zhou%2C+Olivier+Bousquet%2C+Thomas+Navin+Lal%2C+Jason+Weston%2C+and+Bernhard+Scho%CC%88lkopf%2E+2003%2E)