Justifying black-box predictions with domain knowledge

Abstract

AF-CBA uses case-based argumentation to justify classifier predictions by arguing about differences between cases. We extend the mechanism by modelling which differences can compensate for each other by constructing arguments using domain knowledge. This involves a secondary argumentation framework. To assist experts in defining the appropriate domain knowledge, we use a rule-based classifier for semi-automated knowledge induction. We use the resulting rule set to derive arguments and demonstrate this with an evaluation procedure.