Следене
Faiza Khan Khattak
Faiza Khan Khattak
Vector institute for AI
Потвърден имейл адрес: columbia.edu
Заглавие
Позовавания
Позовавания
Година
A survey of word embeddings for clinical text
FK Khattak, S Jeblee, C Pou-Prom, M Abdalla, C Meaney, F Rudzicz
Journal of Biomedical Informatics 100, 100057, 2019
2882019
Quality control of crowd labeling through expert evaluation
Faiza Khan Khattak, Ansaf Salleb-Aouissi
Proceedings of the NIPS 2nd Workshop on Computational Social Science and the …, 2011
862011
Extracting relevant information from physician-patient dialogues for automated clinical note taking
S Jeblee, FK Khattak, N Crampton, M Mamdani, F Rudzicz
Proceedings of the tenth international workshop on health text mining and …, 2019
202019
Improving Crowd Labeling through Expert Evaluation.
Faiza Khan Khattak, Ansaf Salleb-Aouissi
AAAI Spring Symposium: Wisdom of the Crowd, 2012
122012
Diving into a large corpus of pediatric notes
A Salleb-Aouissi, A Radeva, R Passonneau, A Tomar, D Waltz
Proc. ICMLWorkshop on Learning from Unstructured Clinical Text, 2011
112011
AutoScribe: extracting clinically pertinent information from patient-clinician dialogues
FK Khattak, S Jeblee, N Crampton, M Mamdani, F Rudzicz
MEDINFO 2019: Health and Wellbeing e-Networks for All, 1512-1513, 2019
102019
Robust crowd labeling using little expertise
Faiza Khan Khattak, Ansaf Salleb-Aouissi
International Conference on Discovery Science, 94-109, 2013
92013
Toward a Robust and Universal Crowd Labeling Framework
Faiza Khan Khattak
Columbia University, 2017
82017
Soft-prompt tuning for large language models to evaluate bias
JJ Tian, D Emerson, SZ Miyandoab, D Pandya, L Seyyed-Kalantari, ...
arXiv preprint arXiv:2306.04735, 2023
52023
Can Instruction Fine-Tuned Language Models Identify Social Bias through Prompting?
O Dige, JJ Tian, D Emerson, FK Khattak
arXiv preprint arXiv:2307.10472, 2023
42023
MLHOps: machine learning for healthcare operations
FK Khattak, V Subasri, A Krishnan, E Dolatabadi, D Pandya, ...
arXiv preprint arXiv:2305.02474, 2023
42023
Using chain-of-thought prompting for interpretable recognition of social bias
JJ Tian, O Dige, D Emerson, F Khattak
Socially Responsible Language Modelling Research, 2023
42023
Systems and methods for extracting information from a dialogue
FK KHATTAK, F Rudzicz, M Mamdani, N Crampton, S Jeblee
US Patent App. 17/675,189, 2022
42022
An experimental evaluation of transformer-based language models in the biomedical domain
P Grouchy, S Jain, M Liu, K Wang, M Tian, N Arora, H Ngai, FK Khattak, ...
arXiv preprint arXiv:2012.15419, 2020
42020
Biaskg: Adversarial knowledge graphs to induce bias in large language models
CF Luo, A Ghawanmeh, X Zhu, FK Khattak
arXiv preprint arXiv:2405.04756, 2024
22024
Predicting ICU transfers using text messages between nurses and doctors
FK Khattak, C Pou-Prom, R Wu, F Rudzicz
Proceedings of the 2nd Clinical Natural Language Processing Workshop, 89-94, 2019
22019
Toward a robust crowd-labeling framework using expert evaluation and pairwise comparison
FK Khattak, A Salleb-Aouissi
arXiv preprint arXiv:1607.02174, 2016
22016
Can Machine Unlearning Reduce Social Bias in Language Models?
O Dige, D Arneja, TF Yau, Q Zhang, M Bolandraftar, X Zhu, F Khattak
Proceedings of the 2024 Conference on Empirical Methods in Natural Language …, 2024
12024
Mitigating social biases in language models through unlearning
O Dige, D Singh, TF Yau, Q Zhang, B Bolandraftar, X Zhu, FK Khattak
arXiv preprint arXiv:2406.13551, 2024
12024
The Impact of Unstated Norms in Bias Analysis of Language Models
F Kohankhaki, DB Emerson, JJ Tian, L Seyyed-Kalantari, FK Khattak
arXiv preprint arXiv:2404.03471, 2024
12024
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–20