NLPGuard: A Framework for Mitigating the Use of Protected Attributes by NLP Classifiers.
Salvatore GrecoKe ZhouLicia CapraTania CerquitelliDaniele QuerciaPublished in: CoRR (2024)
Keyphrases
- main contribution
- artificial intelligence
- natural language
- data streams
- natural language processing
- theoretical framework
- computational linguistics
- neural network
- ensemble classifier
- risk management
- classification algorithm
- svm classifier
- training examples
- naive bayes
- knowledge representation
- support vector
- bayesian networks
- information retrieval