Folgen
Su Lin Blodgett
Su Lin Blodgett
Microsoft Research Montréal
Bestätigte E-Mail-Adresse bei microsoft.com - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Language (Technology) is Power: A Critical Survey of" Bias" in NLP
SL Blodgett, S Barocas, H Daumé III, H Wallach
Proceedings of the 58th Annual Meeting of the Association for Computational …, 2020
9702020
Demographic dialectal variation in social media: A case study of African-American English
SL Blodgett, L Green, B O'Connor
Proceedings of the Conference on Empirical Methods in Natural Language …, 2016
3822016
Stereotyping Norwegian Salmon: An Inventory of Pitfalls in Fairness Benchmark Datasets
SL Blodgett, G Lopez, A Olteanu, R Sim, H Wallach
Proceedings of the 59th Annual Meeting of the Association for Computational …, 2021
1982021
Racial Disparity in Natural Language Processing: A Case Study of Social Media African-American English
SL Blodgett, B O'Connor
arXiv preprint arXiv:1707.00061, 2017
1712017
A Survey of Race, Racism, and Anti-Racism in NLP
A Field, SL Blodgett, Z Waseem, Y Tsvetkov
Proceedings of the 59th Annual Meeting of the Association for Computational …, 2021
972021
Twitter Universal Dependency Parsing for African-American and Mainstream American English
SL Blodgett, J Wei, B O’Connor
Proceedings of the 56th Annual Meeting of the Association for Computational …, 2018
682018
Evaluating the Social Impact of Generative AI Systems in Systems and Society
I Solaiman, Z Talat, W Agnew, L Ahmad, D Baker, SL Blodgett, ...
arXiv preprint arXiv:2306.05949, 2023
392023
The meaning and measurement of bias: lessons from natural language processing
AZ Jacobs, SL Blodgett, S Barocas, H Daumé III, H Wallach
Proceedings of the 2020 Conference on Fairness, Accountability, and …, 2020
292020
A Dataset and Classifier for Recognizing Social Media English
SL Blodgett, J Wei, B O'Connor
Proceedings of the 3rd Workshop on Noisy User-generated Text, 56-61, 2017
282017
Deconstructing NLG Evaluation: Evaluation Practices, Assumptions, and Their Implications
K Zhou, SL Blodgett, A Trischler, H Daumé III, K Suleman, A Olteanu
Proceedings of the North American Chapter of the Association for …, 2022
222022
Sociolinguistically Driven Approaches for Just Natural Language Processing
SL Blodgett
222021
Risks of AI Foundation Models in Education
SL Blodgett, M Madaio
arXiv preprint arXiv:2110.10024, 2021
182021
Taxonomizing and measuring representational harms: A look at image tagging
J Katzman, A Wang, M Scheuerman, SL Blodgett, K Laird, H Wallach, ...
Proceedings of the AAAI Conference on Artificial Intelligence 37 (12), 14277 …, 2023
172023
Responsible Language Technologies: Foreseeing and Mitigating Harms
SL Blodgett, QV Liao, A Olteanu, R Mihalcea, M Muller, MK Scheuerman, ...
CHI Conference on Human Factors in Computing Systems Extended Abstracts, 1-3, 2022
162022
Monte Carlo Syntax Marginals for Exploring and Using Dependency Parses
KA Keith, SL Blodgett, B O'Connor
Proceedings of the North American Chapter of the Association for …, 2018
132018
FairPrism: Evaluating Fairness-Related Harms in Text Generation
E Fleisig, A Amstutz, C Atalla, SL Blodgett, H Daumé III, A Olteanu, ...
Proceedings of the 61st Annual Meeting of the Association for Computational …, 2023
122023
This Prompt is Measuring <MASK>: Evaluating Bias Evaluation in Language Models
S Goldfarb-Tarrant, E Ungless, E Balkir, SL Blodgett
Findings of ACL, 2023
112023
Examining Responsibility and Deliberation in AI Impact Statements and Ethics Reviews
D Liu, P Nanayakkara, SA Sakha, G Abuhamad, SL Blodgett, ...
Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society, 424-435, 2022
82022
It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance
A Subramonian, X Yuan, H Daumé III, SL Blodgett
Findings of ACL, 2023
62023
How to Write a Bias Statement: Recommendations for Submissions to the Workshop on Gender Bias in NLP
C Hardmeier, MR Costa-jussà, K Webster, W Radford, SL Blodgett
arXiv preprint arXiv:2104.03026, 2021
62021
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20