From text saliency to linguistic objects: learning linguistic interpretable markers with a multi-channels convolutional architecture - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

From text saliency to linguistic objects: learning linguistic interpretable markers with a multi-channels convolutional architecture

Résumé

A lot of effort is currently made to provide methods to analyze and understand deep neural network impressive performances for tasks such as image or text classification. These methods are mainly based on visualizing the important input features taken into account by the network to build a decision. However these techniques, let us cite LIME, SHAP, Grad-CAM, or TDS, require extra effort to interpret the visualization with respect to expert knowledge. In this paper, we propose a novel approach to inspect the hidden layers of a fitted CNN in order to extract interpretable linguistic objects from texts exploiting classification process. In particular, we detail a weighted extension of the Text Deconvolution Saliency (wTDS) measure which can be used to highlight the relevant features used by the CNN to perform the classification task. We empirically demonstrate the efficiency of our approach on corpora from two different languages: English and French. On all datasets, wTDS automatically encodes complex linguistic objects based on co-occurrences and possibly on grammatical and syntax analysis.
Fichier principal
Vignette du fichier
wTDS_HAL.pdf (980.35 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03142170 , version 1 (15-02-2021)

Identifiants

  • HAL Id : hal-03142170 , version 1

Citer

Laurent Vanni, Marco Corneli, Damon Mayaffre, Frédéric Precioso. From text saliency to linguistic objects: learning linguistic interpretable markers with a multi-channels convolutional architecture. 2021. ⟨hal-03142170⟩
78 Consultations
60 Téléchargements

Partager

Gmail Facebook X LinkedIn More