S
Zodix
Study
Academic Library
Search
Dashboard
Shelves
Open access
My library
Inbox
Notes
Write
Learn
Alerts
More
Ask your library
Notifications
Quick cite
Review
Search or jump to…
⌘K
Kai-Wei Chang · Study
Home
/
Author
Kai-Wei Chang
26 works
· latest 2023
· 7 institutions
cluster: provisional
ORCID 0000-0001-5365-0072
Follow
Suggest an ORCID correction
h-index
25
i10
26
Citations
5,312
Works here
26
15
16
17
19
20
21
22
23
Most cited in this library
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
2016 · 1,615 citations
Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
2017 · 829 citations
Mitigating Gender Bias in Natural Language Processing: Literature Review
2019 · 491 citations
The Woman Worked as a Babysitter: On Biases in Language Generation
2019 · 430 citations
Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations
2019 · 355 citations
Works
26 shown
Factoring the Matrix of Domination: A Critical Review and Reimagination of Intersectionality in AI Fairness
Proceedings of the AAAI/ACM Conference on AI Ethics and Society
·
2023
·
5 authors
·
other
·
Open access
47
citations
“I’m fully who I am”: Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation
ACM Conference on Fairness, Accountability, and Transparency (FAccT)
·
2023
·
8 authors
·
other
·
Open access
43
citations
“Kelly is a Warm Person, Joseph is a Role Model”: Gender Biases in LLM-Generated Reference Letters
Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
·
2023
·
6 authors
·
other
·
Open access
139
citations
Integrating topic modeling and word embedding to characterize violent deaths
Proceedings of the National Academy of Sciences
·
2022
·
5 authors
·
Open access
40
citations
How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?
Conference on Empirical Methods in Natural Language Processing (EMNLP)
·
2022
·
3 authors
·
other
·
Open access
55
citations
On Measures of Biases and Harms in NLP
·
2022
·
11 authors
·
other
·
Open access
48
citations
On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations
Annual Meeting of the Association for Computational Linguistics (ACL)
·
2022
·
7 authors
·
other
·
Open access
44
citations
Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal
Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
·
2022
·
8 authors
·
other
·
Open access
28
citations
Revealing Persona Biases in Dialogue Systems
arXiv (Cornell University)
·
2021
·
4 authors
·
preprint
·
Open access
21
citations
Societal Biases in Language Generation: Progress and Challenges
·
2021
·
4 authors
·
other
·
Open access
131
citations
Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies
Conference on Empirical Methods in Natural Language Processing (EMNLP)
·
2021
·
6 authors
·
other
·
Open access
125
citations
Towards Controllable Biases in Language Generation
Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
·
2020
·
4 authors
·
other
·
Open access
89
citations
Mitigating Gender Bias Amplification in Distribution by Posterior Regularization
Annual Meeting of the Association for Computational Linguistics (ACL)
·
2020
·
3 authors
·
other
·
Open access
30
citations
Towards Understanding Gender Bias in Relation Extraction
Proceedings of the conference - Association for Computational Linguistics. Meeting
·
2020
·
10 authors
·
other
·
Open access
26
citations
Bias and Fairness in Natural Language Processing
·
2019
·
3 authors
44
citations
Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations
IEEE/CVF International Conference on Computer Vision (ICCV)
·
2019
·
5 authors
·
other
·
Open access
355
citations
Mitigating Gender Bias in Natural Language Processing: Literature Review
arXiv (Cornell University)
·
2019
·
10 authors
·
preprint
·
Open access
34
citations
Gender Bias in Contextualized Word Embeddings
arXiv (Cornell University)
·
2019
·
6 authors
·
preprint
·
Open access
33
citations
Mitigating Gender Bias in Natural Language Processing: Literature Review
Annual Meeting of the Association for Computational Linguistics (ACL)
·
2019
·
10 authors
·
other
·
Open access
491
citations
The Woman Worked as a Babysitter: On Biases in Language Generation
Conference on Empirical Methods in Natural Language Processing (EMNLP)
·
2019
·
4 authors
·
other
·
Open access
430
citations
Gender Bias in Contextualized Word Embeddings
Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)
·
2019
·
6 authors
·
other
·
Open access
334
citations
Examining Gender Bias in Languages with Grammatical Gender
Conference on Empirical Methods in Natural Language Processing (EMNLP)
·
2019
·
6 authors
·
other
·
Open access
77
citations
Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
Conference on Empirical Methods in Natural Language Processing (EMNLP)
·
2017
·
5 authors
·
other
·
Open access
829
citations
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
arXiv (Cornell University)
·
2016
·
5 authors
·
preprint
·
Open access
1,615
citations
Quantifying and Reducing Stereotypes in Word Embeddings
OpenBU (Boston University)
·
2016
·
5 authors
·
other
·
Open access
57
citations
Learning to Search Better Than Your Teacher
arXiv (Cornell University)
·
2015
·
5 authors
·
preprint
·
Open access
147
citations