Sunipa Dev
Sunipa Dev
Senior Research Scientist, Google
Verified email at - Homepage
Cited by
Cited by
Palm: Scaling language modeling with pathways
A Chowdhery, S Narang, J Devlin, M Bosma, G Mishra, A Roberts, ...
Journal of Machine Learning Research 24 (240), 1-113, 2023
Palm 2 technical report
R Anil, AM Dai, O Firat, M Johnson, D Lepikhin, A Passos, S Shakeri, ...
arXiv preprint arXiv:2305.10403, 2023
On Measuring and Mitigating Biased Inferences of Word Embeddings
S Dev, T Li, J Phillips, V Srikumar
AAAI 2020, 2019
Attenuating Bias in Word Vectors
S Dev, J Phillips
The 22nd International Conference on Artificial Intelligence and Statistics ˇK, 2019
Harms of gender exclusivity and challenges in non-binary representation in language technologies
S Dev, M Monajatipoor, A Ovalle, A Subramonian, JM Phillips, KW Chang
EMNLP, 2021
OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings. arXiv
S Dev, T Li, JM Phillips, V Srikumar
EMNLP, 2021
On measures of Biases and Harms in NLP
S Dev, E Sheng, J Zhao, J Sun, Y Hou, M Sanseverino, J Kim, N Peng, ...
arXiv e-prints, arXiv: 2108.03362, 2021
Socially Aware Bias Measurements for Hindi Language Representations.
V Malik, S Dev, A Nishi, N Peng, KW Chang
NAACL-HLT, 1041-1052, 2022
Re-contextualizing fairness in NLP: The case of India
S Bhatt, S Dev, P Talukdar, S Dave, V Prabhakaran
arXiv preprint arXiv:2209.12226, 2022
Closed Form Word Embedding Alignment
S Dev, S Hassan, JM Phillips
" I wouldnˇ¦t say offensive but...": Disability-Centered Perspectives on Large Language Models
V Gadiraju, S Kane, S Dev, A Taylor, D Wang, E Denton, R Brewer
Proceedings of the 2023 ACM Conference on Fairness, Accountability, and ˇK, 2023
Representation Learning for Resource-Constrained Keyphrase Generation
D Wu, WU Ahmad, S Dev, KW Chang
arXiv preprint arXiv:2203.08118, 2022
VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations
R Archit, S Dev, JM Phillips, V Srikumar, Y Zheng, CCM Yeh, J Wang, ...
ACM transactions on interactive intelligent systems, 2023
Disinfomeme: A multimodal dataset for detecting meme intentionally spreading out disinformation
J Qu, LH Li, J Zhao, S Dev, KW Chang
arXiv preprint arXiv:2205.12617, 2022
The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks
NR Selvam, S Dev, D Khashabi, T Khot, KW Chang
arXiv preprint arXiv:2210.10040, 2022
MISGENDERED: Limits of Large Language Models in Understanding Pronouns
T Hossain, S Dev, S Singh
arXiv preprint arXiv:2306.03950, 2023
Building Stereotype Repositories with Complementary Approaches for Scale and Depth
S Dev, A Jha, J Goyal, D Tewari, S Dave, V Prabhakaran
Proceedings of the First Workshop on Cross-Cultural Considerations in NLP ˇK, 2023
SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models
A Jha, A Davani, CK Reddy, S Dave, V Prabhakaran, S Dev
arXiv preprint arXiv:2305.11840, 2023
Feature subspace isolation and disentanglement in merchant embeddings
DEV Sunipa, Y Zheng, W Zhang
US Patent App. 16/596,665, 2021
Auditing algorithmic fairness in machine learning for health with severity-based LOGAN
A Ovalle, S Dev, J Zhao, M Sarrafzadeh, KW Chang
International Workshop on Health Intelligence, 123-136, 2023
The system can't perform the operation now. Try again later.
Articles 1–20