Fair NLP Models with Differentially Private Text Encoders
Gaurav Maheshwari | Pascal Denis | Mikaela Keller | Aurélien Bellet
Findings of the Association for Computational Linguistics: EMNLP 2022
Encoded text representations often capture sensitive attributes about individuals (e.g., race or gender), which raise privacy concerns and can make downstream models unfair to certain groups. In this work, we propose FEDERATE, an approach that combines ideas from differential privacy and adversarial training to learn private text representations which also induces fairer models. We empirically evaluate the trade-off between the privacy of the representations and the fairness and accuracy of the downstream model on four NLP datasets. Our results show that FEDERATE consistently improves upon previous methods, and thus suggest that privacy and fairness can positively reinforce each other.
What Musical Knowledge Does Self-Attention Learn ?
Gabriel Loiseau | Mikaela Keller | Louis Bigo
Proceedings of the 2nd Workshop on NLP for Music and Spoken Audio (NLP4MusA)
Investigating Lexical Substitution Scoring for Subtitle Generation
Oren Glickman | Ido Dagan | Walter Daelemans | Mikaela Keller | Samy Bengio
Proceedings of the Tenth Conference on Computational Natural Language Learning (CoNLL-X)
- Gaurav Maheshwari 1
- Pascal Denis 1
- Aurélien Bellet 1
- Gabriel Loiseau 1
- Louis Bigo 1
- show all...