Counterfactual Fairness in Text Classification through Robustness

    Sahaj Garg
    Sahaj Garg
    Vincent Perot
    Vincent Perot
    Nicole Limtiaco
    Nicole Limtiaco

    national conference on artificial intelligence, 2019.

    Cited by: 1|Bibtex|Views21|Links
    EI

    Abstract:

    In this paper, we study counterfactual fairness in text classification, which asks the question: How would the prediction change if the sensitive attribute discussed in the example were something else? We offer a heuristic for measuring this particular form of fairness in text classifiers by substituting individual tokens pertaining to at...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments