Measuring Imbalance on Intersectional Protected Attributes and on Target Variable to Forecast Unfair Classifications
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Access"
DOI: 10.1109/access.2023.3252370
Abstract: Bias in software systems is a serious threat to human rights: when software makes decisions that allocate resources or opportunities, may disparately impact people based on personal traits (e.g., gender, ethnic group, etc.), systematically (dis)advantaging… read more here.
Keywords: protected attributes; balance; measuring imbalance; target variable ... See more keywords
NLPGuard: A Framework for Mitigating the Use of Protected Attributes by NLP Classifiers
Sign Up to like & getrecommendations! Published in 2024 at "Proceedings of the ACM on Human-Computer Interaction"
DOI: 10.1145/3686924
Abstract: AI regulations are expected to prohibit machine learning models from using sensitive attributes during training. However, the latest Natural Language Processing (NLP) classifiers, which rely on deep learning, operate as black-box systems, complicating the detection… read more here.
Keywords: framework mitigating; attributes nlp; protected attributes; language ... See more keywords