Litcius/Paper detail

Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection

Giuseppe Attanasio, Debora Nozza, Eliana Pastor, Dirk Hovy

202217 citationsDOIOpen Access PDF

Abstract

Warning: This paper contains examples of language that some people may find offensive.

Topics & Concepts

InterpretabilityComputer scienceBenchmarkingTransformerArtificial intelligenceNatural language processingMachine learningSecurity tokenAttributionSpeech recognitionPsychologyComputer securitySocial psychologyQuantum mechanicsMarketingVoltagePhysicsBusinessHate Speech and Cyberbullying DetectionAdversarial Robustness in Machine LearningExplainable Artificial Intelligence (XAI)
Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection | Litcius