Text Deconvolution Saliency (TDS) : a deep tool box for linguistic analysis - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Text Deconvolution Saliency (TDS) : a deep tool box for linguistic analysis

Résumé

In this paper, we propose a new strategy , called Text Deconvolution Saliency (TDS), to visualize linguistic information detected by a CNN for text classification. We extend Deconvolution Networks to text in order to present a new perspective on text analysis to the linguistic community. We empirically demonstrated the efficiency of our Text Decon-volution Saliency on corpora from three different languages: English, French, and Latin. For every tested dataset, our Text Deconvolution Saliency automatically encodes complex linguistic patterns based on co-occurrences and possibly on grammatical and syntax analysis.
Fichier principal
Vignette du fichier
acl2018.pdf (1.08 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01804310 , version 1 (31-05-2018)

Identifiants

  • HAL Id : hal-01804310 , version 1

Citer

Laurent Vanni, Mélanie Ducoffe, Damon Mayaffre, Frédéric Precioso, Dominique Longrée, et al.. Text Deconvolution Saliency (TDS) : a deep tool box for linguistic analysis. 56th Annual Meeting of the Association for Computational Linguistics, Jul 2018, Melbourne, France. ⟨hal-01804310⟩
436 Consultations
871 Téléchargements

Partager

Gmail Facebook X LinkedIn More