CoChat
Sign Up
Cited by 241Ethics and Social Impacts of AINatural Language Processing TechniquesTopic Modeling

Predictive biases in natural language processing models: A conceptual framework and overview

Open access
Shah, Deven Santosh, Schwartz, H. Andrew, Hovy, Dirk·2020·Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
DOI 10.18653/v1/2020.acl-main.468
Open this paper in CoChat — free accountOpen PDF

Abstract

An increasing number of natural language processing papers address the effect of bias on predictions, introducing mitigation techniques at different parts of the standard NLP pipeline (data and models).However, these works have been conducted individually, without a unifying framework to organize efforts within the field.This situation leads to repetitive approaches, and focuses overly on bias symptoms/effects, rather than on their origins, which could limit the development of effective countermeasures.In this paper, we propose a unifying predictive bias framework for NLP.We summarize the NLP literature and suggest general mathematical definitions of predictive bias.We differentiate two consequences of bias: outcome disparities and error disparities, as well as four potential origins of biases: label bias, selection bias, model overamplification, and semantic bias.Our framework serves as an overview of predictive bias in NLP, integrating existing work into a single structure, and providing a conceptual baseline for improved frameworks.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.18653/v1/2020.acl-main.468

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Training data used to train an LLM may be drawn from a nonrepresentative sample of the population, which can cause the model to fail to generalize well to some social groups.

    “Training Data: The data used to train an LLM may be drawn from a nonrepresentative sample of the population, which can cause the model to fail to generalize well to some social groups.”

    From Bias and Fairness in Large Language Models: A Survey (2024) · cites this paper as Shah, Schwartz, and Hovy 2020

    Section 3 (“Four Origins of Bias”) links unrepresentative training data to lower accuracy for demographic groups, and Appendix A.2 says models trained on demographically mismatched samples perform significantly worse. Those passages support the claimed mechanism for NLP models, but the paper’s examples concern tools such as taggers and parsers rather than LLMs specifically. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

  • Training data may omit important contexts, and proxies used as labels may incorrectly measure the actual outcome of interest.

    “The data may omit important contexts, and proxies used as labels ( e.g. , sentiment) may incorrectly measure the actual outcome of interest ( e.g. , representational harms).”

    From Bias and Fairness in Large Language Models: A Survey (2024) · cites this paper as Shah, Schwartz, and Hovy 2020

    Section 3, “Four Origins of Bias” (page unavailable), describes selection bias from non-representative training observations and label bias from erroneous labels. Section 2 also describes annotators failing to account for authors’ racial background and sociolinguistic norms. These passages support the concern about missing context and flawed labels, but they do not establish the specific claim that a proxy label such as sentiment incorrectly measures an outcome such as representational harm. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

  • Bias emerges at points within the model development and deployment process, which may exacerbate preexisting historical biases.

    “Another way of understanding social bias in LLMs is to examine at which points within the model development and deployment process the bias emerges, which may exacerbate preexisting historical biases. This has been thoroughly explored by Mehrabi et al. (2021), Shah, Schwartz, and Hovy (2020), and Suresh and Guttag (2021), and we summarize these pathways here:”

    From Bias and Fairness in Large Language Models: A Survey (2024) · cites this paper as Shah, Schwartz, and Hovy 2020

  • The aggregation of data may obscure distinct social groups that should be treated differently.

    “The aggregation of data may also obscure distinct social groups that should be treated differently, causing the model”

    From Bias and Fairness in Large Language Models: A Survey (2024) · cites this paper as Shah, Schwartz, and Hovy 2020

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 86

  1. Jussara M Almeida, Gisele L Pappa, et al. 2015. Twit- ter population sample bias and its impact on predic- tive outcomes: A case study on elections. In Pro- ceedings of the 2015 IEEE/ACM International Con- ference on Advances in Social Networks Analysis and Mining 2015, pages 1254-1261. ACM.
  2. Fatemeh Almodaresi, Lyle Ungar, Vivek Kulkarni, Mohsen Zakeri, Salvatore Giorgi, and H. Andrew Schwartz. 2017. On the distribution of lexical fea- tures at multiple levels of analysis. In The 55th An- nual Meeting of the Association for Computational Linguistics.
  3. Ron Artstein and Massimo Poesio. 2008. Inter-coder agreement for computational linguistics. Computa- tional Linguistics, 34(4):555-596.
  4. Reg Baker, J Michael Brick, Nancy A Bates, Mike Battaglia, Mick P Couper, Jill A Dever, Krista J Gile, and Roger Tourangeau. 2013. Summary re- port of the aapor task force on non-probability sam- pling. Journal of Survey Statistics and Methodology, 1(2):90-143.
  5. Roy F Baumeister, Kathleen D Vohs, and David C Fun- der. 2007. Psychology as the science of self-reports and finger movements: Whatever happened to actual behavior? Perspectives on Psychological Science, 2(4):396-403.
  6. Emily M Bender and Batya Friedman. 2018. Data statements for natural language processing: Toward mitigating system bias and enabling better science. Transactions of the Association for Computational Linguistics, 6:587-604.
  7. Adrian Benton, Margaret Mitchell, and Dirk Hovy. 2017. Multitask learning for mental health condi- tions with limited social media data. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Vol- ume 1, Long Papers, volume 1, pages 152-162.
  8. Richard A Berk. 1983. An introduction to sample se- lection bias in sociological data. American Socio- logical Review, pages 386-398.
  9. Sudeep Bhatia. 2017. Associative judgment and vector space semantics. Psychological review, 124(1):1.
  10. Su Lin Blodgett and Brendan O'Connor. 2017. Racial disparity in natural language processing: A case study of social media African-American English. arXiv preprint arXiv:1707.00061. · arXiv
  11. Tolga Bolukbasi, Kai-Wei Chang, James Y Zou, Venkatesh Saligrama, and Adam T Kalai. 2016. Man is to computer programmer as woman is to homemaker? debiasing word embeddings. In Ad- vances in neural information processing systems, pages 4349-4357.
  12. Aylin Caliskan, Joanna J Bryson, and Arvind Narayanan. 2017. Semantics derived automatically from language corpora contain human-like biases. Science, 356(6334):183-186.
  13. Murphy Choy, Michelle Cheong, Ma Nang Laik, and Koo Ping Shung. 2012. Us presidential elec- tion 2012 prediction using census corrected twitter model. arXiv preprint arXiv:1211.0938. · arXiv
  14. Murphy Choy, Michelle LF Cheong, Ma Nang Laik, and Koo Ping Shung. 2011. A sentiment analy- sis of singapore presidential election 2011 using twitter data with census correction. arXiv preprint arXiv:1108.5520. · arXiv
  15. Christopher Clark, Mark Yatskar, and Luke Zettle- moyer. 2019. Donâ Ȃ Źt take the easy way out: En- semble based methods for avoiding known dataset biases. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natu- ral Language Processing (EMNLP-IJCNLP), pages 4060-4073.
  16. Maximin Coavoux, Shashi Narayan, and Shay B Co- hen. 2018. Privacy-preserving neural representa- tions of text. In Proceedings of the 2018 Confer- ence on Empirical Methods in Natural Language Processing, pages 1-10.
  17. Glen Coppersmith, Mark Dredze, Craig Harman, Kristy Hollingshead, and Margaret Mitchell. 2015. Clpsych 2015 shared task: Depression and ptsd on twitter. In CLPsych@ HLT-NAACL, pages 31-39.
  18. Sam Corbett-Davies and Sharad Goel. 2018. The measure and mismeasure of fairness: A critical review of fair machine learning. arXiv preprint arXiv:1808.00023. · arXiv
  19. Fintan Costello and Paul Watts. 2014. Surprisingly ra- tional: Probability theory plus noise explains biases in judgment. Psychological review, 121(3):463.
  20. Mick P Couper. 2013. Is the sky falling? new tech- nology, changing media, and the future of surveys. In Survey Research Methods, volume 7, pages 145- 156.
  21. Aron Culotta. 2014. Reducing sampling bias in social media data for county health inference. In Joint Sta- tistical Meetings Proceedings, pages 1-12.
  22. Cristian Danescu-Niculescu-Mizil, Robert West, Dan Jurafsky, Jure Leskovec, and Christopher Potts. 2013. No country for old members: User lifecy- cle and linguistic change in online communities. In Proceedings of the 22nd international conference on World Wide Web, pages 307-318.
  23. Hal Daume III. 2007. Frustratingly easy domain adap- tation. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 256-263.
  24. Jacob Eisenstein, Brendan O'Connor, Noah A Smith, and Eric P Xing. 2010. A latent variable model for geographic lexical variation. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 1277-1287. Associa- tion for Computational Linguistics.
  25. Yanai Elazar and Yoav Goldberg. 2018. Adversarial removal of demographic attributes from text data. In Proceedings of the 2018 Conference on Empiri- cal Methods in Natural Language Processing, pages 11-21.
  26. Sorelle A Friedler, Carlos Scheidegger, and Suresh Venkatasubramanian. 2016. On the (im) possibility of fairness. corr abs/1609.07236 (2016). · arXiv
  27. Nikhil Garg, Londa Schiebinger, Dan Jurafsky, and James Zou. 2018. Word embeddings quantify 100 years of gender and ethnic stereotypes. Pro- ceedings of the National Academy of Sciences, 115(16):E3635-E3644.
  28. Aparna Garimella, Carmen Banea, Dirk Hovy, and Rada Mihalcea. 2019. Women's syntactic resilience and men's grammatical luck: Gender-bias in part- of-speech tagging and dependency parsing. In Pro- ceedings of the 57th Annual Meeting of the Asso- ciation for Computational Linguistics, pages 3493- 3498, Florence, Italy. Association for Computa- tional Linguistics.
  29. Timnit Gebru, Jamie Morgenstern, Briana Vecchione, Jennifer Wortman Vaughan, Hanna Wallach, Hal Daumé III, and Kate Crawford. 2018. Datasheets for datasets. In Proceedings of the 5 th Workshop on Fairness, Accountability, and Transparency in Ma- chine Learning, Stockholm, Sweden.
  30. Salvatore Giorgi, Veronica Lynn, Keshav Gupta, San- dra Matz, Lyle Ungar, and H.A. Schwartz. 2019. Correcting sociodemographic selection biases for population prediction. ArXiv.
  31. Bruce Glymour and Jonathan Herington. 2019. Mea- suring the biases that matter: The ethical and ca- sual foundations for measures of fairness in algo- rithms. In Proceedings of the Conference on Fair- ness, Accountability, and Transparency, FAT* '19, pages 269-278, New York, NY, USA. ACM. · DOI · Paper page
  32. 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 Computa- tional Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 609-614. · DOI · Paper page
  33. Ron D Hays, Honghu Liu, and Arie Kapteyn. 2015. Use of internet panels to conduct surveys. Behavior research methods, 47(3):685-690.
  34. Lisa Anne Hendricks, Kaylee Burns, Kate Saenko, Trevor Darrell, and Anna Rohrbach. 2018. Women also snowboard: Overcoming bias in captioning models. In European Conference on Computer Vi- sion, pages 793-811. Springer.
  35. Joseph Henrich, Steven J Heine, and Ara Norenzayan. 2010. The weirdest people in the world? Behav- ioral and brain sciences, 33(2-3):61-83.
  36. Miguel A Hernán, Sonia Hernández-Díaz, and James M Robins. 2004. A structural approach to selection bias. Epidemiology, pages 615-625.
  37. Yasmeen Hitti, Eunbee Jang, Ines Moreno, and Car- olyne Pelletier. 2019. Proposed taxonomy for gen- der bias in text; a filtering methodology for the gen- der generalization subtype. In Proceedings of the First Workshop on Gender Bias in Natural Language Processing, pages 8-17, Florence, Italy. Association for Computational Linguistics.
  38. Dirk Hovy. 2015. Demographic factors improve clas- sification performance. In Proceedings of the 53rd Annual Meeting of the Association for Computa- tional Linguistics and the 7th International Joint Conference on Natural Language Processing (Vol- ume 1: Long Papers), volume 1, pages 752-762.
  39. Dirk Hovy. 2018. The social and the neural net- work: How to make natural language processing about people again. In Proceedings of the Sec- ond Workshop on Computational Modeling of Peo- pleâ Ȃ Źs Opinions, Personality, and Emotions in So- cial Media, pages 42-49.
  40. Dirk Hovy, Taylor Berg-Kirkpatrick, Ashish Vaswani, and Eduard Hovy. 2013. Learning whom to trust with mace. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1120-1130.
  41. Dirk Hovy, Federico Bianchi, and Tommaso Forna- ciari. 2020. Can you translate that into man? com- mercial machine translation systems include stylis- tic biases. In Proceedings of the 58th Annual Meet- ing of the Association for Computational Linguis- tics, Seattle, WA, USA. Association for Computa- tional Linguistics.
  42. Dirk Hovy and Anders Søgaard. 2015. Tagging perfor- mance correlates with author age. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), volume 2, pages 483-488.
  43. Dirk Hovy and Shannon L Spruit. 2016. The social impact of natural language processing. In Proceed- ings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Pa- pers), volume 2, pages 591-598.
  44. Jing Jiang and ChengXiang Zhai. 2007. Instance weighting for domain adaptation in nlp. In Proceed- ings of the 45th annual meeting of the association of computational linguistics, pages 264-271.
  45. Anna Jørgensen, Dirk Hovy, and Anders Søgaard. 2015. Challenges of studying and processing di- alects in social media. In Proceedings of the Work- shop on Noisy User-generated Text, pages 9-18.
  46. Kenneth Joseph, Lisa Friedland, William Hobbs, Oren Tsur, and David Lazer. 2017. Constance: Modeling annotation contexts to improve stance classification. arXiv preprint arXiv:1708.06309. · arXiv
  47. David Jurgens. 2013. That's what friends are for: Infer- ring location in online social media platforms based on social relationships. In Seventh International AAAI Conference on Weblogs and Social Media.
  48. David Jurgens, Yulia Tsvetkov, and Dan Jurafsky. 2017. Incorporating dialectal variability for socially equitable language identification. In Proceedings of the 55th Annual Meeting of the Association for Com- putational Linguistics (Volume 2: Short Papers), pages 51-57.
  49. ML Kern, G Park, JC Eichstaedt, HA Schwartz, M Sap, LK Smith, and LH Ungar. 2016. Gaining insights from social media language: Methodologies and challenges. Psychological methods, 21(4):507-525.
  50. Svetlana Kiritchenko and Saif Mohammad. 2018. Ex- amining gender and race bias in two hundred sen- timent analysis systems. In Proceedings of the Seventh Joint Conference on Lexical and Computa- tional Semantics, pages 43-53.
  51. Jon Kleinberg, Jens Ludwig, Sendhil Mullainathan, and Cass R Sunstein. 2018. Discrimination in the age of algorithms. Journal of Legal Analysis, 10.
  52. Austin C Kozlowski, Matt Taddy, and James A Evans. 2018. The geometry of culture: Analyzing mean- ing through word embeddings. arXiv preprint arXiv:1803.09288. · arXiv
  53. Keita Kurita, Nidhi Vyas, Ayush Pareek, Alan W Black, and Yulia Tsvetkov. 2019. Measuring bias in contextualized word representations. arXiv preprint arXiv:1906.07337. · arXiv
  54. Yitong Li, Timothy Baldwin, and Trevor Cohn. 2018. Towards robust and privacy-preserving text repre- sentations. In Proceedings of the 56th Annual Meet- ing of the Association for Computational Linguistics (Volume 2: Short Papers), volume 2, pages 25-30.
  55. Thomas Manzini, Yao Chong Lim, Yulia Tsvetkov, and Alan W Black. 2019. Black is to criminal as cau- casian is to police: Detecting and removing mul- ticlass bias in word embeddings. arXiv preprint arXiv:1904.04047. · arXiv
  56. Robert R. McCrae and Paul T. Costa Jr. 1989. Rein- terpreting the Myers-Briggs type indicator from the perspective of the five-factor model of personality. Journal of Personality, 57(1):17-40.
  57. Margaret Mitchell, Simone Wu, Andrew Zaldivar, Parker Barnes, Lucy Vasserman, Ben Hutchinson, Elena Spitzer, Inioluwa Deborah Raji, and Timnit Gebru. 2019. Model cards for model reporting. In Proceedings of the Conference on Fairness, Ac- countability, and Transparency, pages 220-229. ACM.
  58. Ehsan Mohammady and Aron Culotta. 2014. Using county demographics to infer attributes of twitter users. In Proceedings of the joint workshop on so- cial dynamics and personal attributes in social me- dia, pages 7-16.
  59. Malvina Nissim, Rik van Noord, and Rob van der Goot. 2019. Fair is better than sensational: Man is to doctor as woman is to doctor. arXiv preprint arXiv:1905.09866. · arXiv
  60. David K Park, Andrew Gelman, and Joseph Bafumi. 2006. State-level opinions from national surveys: Poststratification using multilevel logistic regres- sion. Public opinion in state politics, pages 209-28.
  61. Rebecca J Passonneau and Bob Carpenter. 2014. The benefits of a model of annotation. Transactions of the Association for Computational Linguistics, 2:311-326.
  62. James W Pennebaker. 2011. The secret life of pro- nouns. New Scientist, 211(2828):42-45.
  63. James W. Pennebaker and Lori D. Stone. 2003. Words of wisdom: Language use over the life span. Journal of Personality and Social Psychology, 85(2):291.
  64. Barbara Plank, Dirk Hovy, and Anders Søgaard. 2014. Learning part-of-speech taggers with inter-annotator agreement loss. In Proceedings of the 14th Confer- ence of the European Chapter of the Association for Computational Linguistics, pages 742-751.
  65. Marcelo OR Prates, Pedro H Avelar, and Luís C Lamb. 2018. Assessing gender bias in machine translation: a case study with google translate. Neural Comput- ing and Applications, pages 1-19.
  66. Daniel Preoţiuc-Pietro, Johannes Eichstaedt, Gregory Park, Maarten Sap, Laura Smith, Victoria Tobolsky, H Andrew Schwartz, and Lyle Ungar. 2015. The role of personality, age, and gender in tweeting about mental illness. In Proceedings of the 2nd workshop on computational linguistics and clinical psychol- ogy: From linguistic signal to clinical reality, pages 21-30.
  67. Daniel Preotiuc-Pietro, Maarten Sap, H Andrew Schwartz, and Lyle Ungar. 2015. Mental illness detection at the world well-being project for the clpsych 2015 shared task. In Proceedings of the Workshop on Computational Linguistics and Clini- cal Psychology: From Linguistic Signal to Clinical Reality, NAACL.
  68. Iyad Rahwan, Manuel Cebrian, Nick Obradovich, Josh Bongard, Jean-François Bonnefon, Cynthia Breazeal, Jacob W Crandall, Nicholas A Christakis, Iain D Couzin, Matthew O Jackson, et al. 2019. Ma- chine behaviour. Nature, 568(7753):477.
  69. Alexey Romanov, Maria De-Arteaga, Hanna Wal- lach, Jennifer Chayes, Christian Borgs, Alexandra Chouldechova, Sahin Geyik, Krishnaram Kentha- padi, Anna Rumshisky, and Adam Tauman Kalai. 2019. What's in a name? reducing bias in bios with- out access to protected attributes. arXiv preprint arXiv:1904.05233. · arXiv
  70. 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), volume 2, pages 8-14.
  71. Maarten Sap, Dallas Card, Saadia Gabriel, Yejin Choi, and Noah A. Smith. 2019. The risk of racial bias in hate speech detection. In Proceedings of the 57th Conference of the Association for Computational Linguistics, pages 1668-1678, Florence, Italy. As- sociation for Computational Linguistics.
  72. H Andrew Schwartz, Johannes C Eichstaedt, Mar- garet L Kern, Lukasz Dziurzynski, Megha Agrawal, Gregory J Park, Shrinidhi K Lakshmikanth, Sneha Jha, Martin EP Seligman, Lyle Ungar, et al. 2013. Characterizing geographic variation in well-being using tweets. In Seventh International AAAI Confer- ence on Weblogs and Social Media (ICWSM 2013).
  73. Gabriel Stanovsky, Noah A. Smith, and Luke Zettle- moyer. 2019. Evaluating gender bias in machine translation. In Proceedings of the 57th Annual Meet- ing of the Association for Computational Linguis- tics, pages 1679-1684, Florence, Italy. Association for Computational Linguistics. · DOI
  74. Tony Sun, Andrew Gaut, Shirlyn Tang, Yuxin Huang, Mai ElSherief, Jieyu Zhao, Diba Mirza, Elizabeth Belding, Kai-Wei Chang, and William Yang Wang. 2019. Mitigating gender bias in natural language processing: Literature review. In Proceedings of the 57th Conference of the Association for Computa- tional Linguistics, pages 1630-1640, Florence, Italy. Association for Computational Linguistics.
  75. Harini Suresh and John V Guttag. 2019. A framework for understanding unintended consequences of ma- chine learning. arXiv preprint arXiv:1901.10002. · arXiv
  76. Chris Sweeney and Maryam Najafian. 2019. A trans- parent framework for evaluating unintended demo- graphic bias in word embeddings. In Proceedings of the 57th Conference of the Association for Com- putational Linguistics, pages 1662-1667, Florence, Italy. Association for Computational Linguistics.
  77. Peter Trudgill. 2000. Sociolinguistics: An introduction to language and society. Penguin UK.
  78. Amos Tversky and Daniel Kahneman. 1973. Availabil- ity: A heuristic for judging frequency and probabil- ity. Cognitive psychology, 5(2):207-232.
  79. Svitlana Volkova, Theresa Wilson, and David Yarowsky. 2013. Exploring demographic lan- guage variations to improve multilingual sentiment analysis in social media. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1815-1827.
  80. Thomas A. Widiger and Douglas B. Samuel. 2005. Diagnostic categories or dimensions? A question for the Diagnostic and Statistical Manual of Men- tal Disorders-Fifth Edition. Journal of Abnormal Psychology, 114(4):494.
  81. Diyi Yang, Robert E Kraut, Tenbroeck Smith, Eli- jah Mayfield, and Dan Jurafsky. 2019. Seekers, providers, welcomers, and storytellers: Modeling social roles in online health communities. In Pro- ceedings of the 2019 CHI Conference on Human Factors in Computing Systems, pages 1-14.
  82. Mark Yatskar, Luke Zettlemoyer, and Ali Farhadi. 2016. Situation recognition: Visual semantic role labeling for image understanding. In Proceedings of the IEEE Conference on Computer Vision and Pat- tern Recognition, pages 5534-5542.
  83. Emilio Zagheni and Ingmar Weber. 2015. Demo- graphic research with non-representative internet data. International Journal of Manpower, 36(1):13- 25.
  84. Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Or- donez, and Kai-Wei Chang. 2017. Men also like shopping: Reducing gender bias amplification us- ing corpus-level constraints. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2979-2989.
  85. Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Or- donez, and Kai-Wei Chang. 2018. Gender bias in coreference resolution: Evaluation and debiasing methods. arXiv preprint arXiv:1804.06876. · arXiv
  86. Ran Zmigrod, Sebastian J. Mielke, Hanna Wallach, and Ryan Cotterell. 2019. Counterfactual data aug- mentation for mitigating gender stereotypes in lan- guages with rich morphology. In Proceedings of the 57th Conference of the Association for Compu- tational Linguistics, pages 1651-1661.

Cited by

Sorted by citations

Authors
Shah, D. S., Schwartz, H. A., & Hovy, D.
Affiliations
  • Stony Brook University (US)
  • Bocconi University (IT)
ORCID
Venue
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Publisher
Association for Computational Linguistics
Published
2020
Pages
5248-5264
ISSN
0736-587X (ISSN-L)
DOI
10.18653/v1/2020.acl-main.468
OpenAlex
W3035377849
Cited by
241
References
1
Citations by year
2026: 11 · 2025: 29 · 2024: 27 · 2023: 46 · 2022: 50 · 2021: 62 · 2020: 16
FWCI
44.02
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
  • Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • Archivio istituzionale della Ricerca - Bocconi (submittedVersion, cc-by)
  • arXiv (Cornell University)
Topics
  • Social Sciences › Safety Research › Ethics and Social Impacts of AI
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
Keywords
predictive bias, algorithmic fairness, bias mitigation, outcome disparities, label bias, selection bias, semantic bias, conceptual framework

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