Téléchargement | - Voir la version finale : Challenges in applying explainability methods to improve the fairness of NLP models (PDF, 275 Kio)
|
---|
Auteur | Rechercher : Balkir, Esma1; Rechercher : Kiritchenko, Svetlana1; Rechercher : Nejadgholi, Isar1; Rechercher : Fraser, Kathleen1 |
---|
Affiliation | - Conseil national de recherches du Canada. Technologies numériques
|
---|
Format | Texte, Article |
---|
Conférence | 2nd Workshop on Trustworthy Natural Language Processing (TrustNLP 2022), July 14, 2022, Seattle, U.S.A. |
---|
Résumé | Motivations for methods in explainable artificial intelligence (XAI) often include detecting, quantifying and mitigating bias, and contributing to making machine learning models fairer. However, exactly how an XAI method can help in combating biases is often left unspecified. In this paper, we briefly review trends in explainability and fairness in NLP research, identify the current practices in which explainability methods are applied to detect and mitigate bias, and investigate the barriers preventing XAI methods from being used more widely in tackling fairness issues. |
---|
Date de publication | 2022-07-14 |
---|
Maison d’édition | Association for Computational Linguistics |
---|
Licence | |
---|
Dans | |
---|
Langue | anglais |
---|
Publications évaluées par des pairs | Oui |
---|
Exporter la notice | Exporter en format RIS |
---|
Signaler une correction | Signaler une correction (s'ouvre dans un nouvel onglet) |
---|
Identificateur de l’enregistrement | 46dba455-4f74-4521-a227-5c02dd74108a |
---|
Enregistrement créé | 2022-09-09 |
---|
Enregistrement modifié | 2022-09-14 |
---|