Extending Logic Explained Networks to Text Classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Extending Logic Explained Networks to Text Classification

Résumé

Recently, Logic Explained Networks (LENs) have been proposed as explainable-by-design neural models providing logic explanations for their predictions. However, these models have only been applied to vision and tabular data, and they mostly favour the generation of global explanations, while local ones tend to be noisy and verbose. For these reasons, we propose LEN p , improving local explanations by perturbing input words, and we test it on text classification. Our results show that (i) LEN p provides better local explanations than LIME in terms of sensitivity and faithfulness, and (ii) logic explanations are more useful and user-friendly than feature scoring provided by LIME as attested by a human survey.
Fichier principal
Vignette du fichier
2211.09732.pdf (791.13 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03863362 , version 1 (21-11-2022)

Identifiants

  • HAL Id : hal-03863362 , version 1

Citer

Rishabh Jain, Gabriele Ciravegna, Pietro Barbiero, Francesco Giannini, Davide Buffelli, et al.. Extending Logic Explained Networks to Text Classification. Empirical Methods in Natural Language Processing, Dec 2022, Abu Dhabi, United Arab Emirates. ⟨hal-03863362⟩
35 Consultations
11 Téléchargements

Partager

Gmail Facebook X LinkedIn More