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.
Liste complète des métadonnées

Cited literature [16 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01804310
Contributor : Laurent Vanni <>
Submitted on : Thursday, May 31, 2018 - 3:56:34 PM
Last modification on : Thursday, February 7, 2019 - 4:13:50 PM
Document(s) archivé(s) le : Saturday, September 1, 2018 - 2:42:20 PM

File

acl2018.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01804310, version 1

Collections

Citation

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〉

Share

Metrics

Record views

232

Files downloads

430