Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Jourdan, Fanny"'
Autor:
Jourdan, Fanny
The burgeoning field of Natural Language Processing (NLP) stands at a critical juncture where the integration of fairness within its frameworks has become an imperative. This PhD thesis addresses the need for equity and transparency in NLP systems, r
Externí odkaz:
http://arxiv.org/abs/2410.12511
Ensuring fairness in NLP models is crucial, as they often encode sensitive attributes like gender and ethnicity, leading to biased outcomes. Current concept erasure methods attempt to mitigate this by modifying final latent representations to remove
Externí odkaz:
http://arxiv.org/abs/2312.06499
This paper presents novel experiments shedding light on the shortcomings of current metrics for assessing biases of gender discrimination made by machine learning algorithms on textual data. We focus on the Bios dataset, and our learning task is to p
Externí odkaz:
http://arxiv.org/abs/2306.05307
Autor:
Jourdan, Fanny, Picard, Agustin, Fel, Thomas, Risser, Laurent, Loubes, Jean Michel, Asher, Nicholas
Transformer architectures are complex and their use in NLP, while it has engendered many successes, makes their interpretability or explainability challenging. Recent debates have shown that attention maps and attribution methods are unreliable (Prut
Externí odkaz:
http://arxiv.org/abs/2305.06754
Autor:
Jourdan, Fanny, Kaninku, Titon Tshiongo, Asher, Nicholas, Loubes, Jean-Michel, Risser, Laurent
Automatic recommendation systems based on deep neural networks have become extremely popular during the last decade. Some of these systems can however be used for applications which are ranked as High Risk by the European Commission in the A.I. act,
Externí odkaz:
http://arxiv.org/abs/2302.14063