Explainability

Investigating the effectiveness of explainability methods in Parkinson’s detection from speech
A systematic test of six explanation methods for a speech-based Parkinson’s detector, showing faithful explanations that domain experts still cannot easily read.
Eleonora Mancini, Francesco Paissan, Paolo Torroni, Mirco Ravanelli, Cem Subakan
Cite DOI
Investigating the effectiveness of explainability methods in Parkinson’s detection from speech
Detecting and explaining unfairness in consumer contracts through memory networks
Memory networks read a knowledge base of expert legal rationales to detect unfair clauses in terms of service and to point to the reasons.
Cite DOI URL
Explaining Potentially Unfair Clauses to the Consumer with the CLAUDETTE tool
CLAUDETTE now tells consumers why a Terms of Service clause may be unfair, by linking each flagged clause to legal rationales written by experts.
Rūta Liepiņa, Federico Ruggeri, Francesca Lagioia, Marco Lippi, Kasper Drazewski, Paolo Torroni
PDF Cite