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

Abstract : 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.
Type de document :
Communication dans un congrès
56th Annual Meeting of the Association for Computational Linguistics, Jul 2018, Melbourne, France
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01804310
Contributeur : Laurent Vanni <>
Soumis le : jeudi 31 mai 2018 - 15:56:34
Dernière modification le : samedi 9 juin 2018 - 01:16:37

Fichier

acl2018.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01804310, version 1

Collections

I3S | BCL | UNICE

Citation

Laurent Vanni, M Ducoffe, D Mayaffre, F. Precioso, D 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〉

Partager

Métriques

Consultations de la notice

23

Téléchargements de fichiers

17