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

Laurent Vanni, Melanie Ducoffe, Carlos Aguilar, Frederic Precioso, Damon Mayaffre


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 Deconvolution 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.
Anthology ID:
P18-1051
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
548–557
Language:
URL:
https://aclanthology.org/P18-1051
DOI:
10.18653/v1/P18-1051
Bibkey:
Cite (ACL):
Laurent Vanni, Melanie Ducoffe, Carlos Aguilar, Frederic Precioso, and Damon Mayaffre. 2018. Textual Deconvolution Saliency (TDS) : a deep tool box for linguistic analysis. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 548–557, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Textual Deconvolution Saliency (TDS) : a deep tool box for linguistic analysis (Vanni et al., ACL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/P18-1051.pdf
Poster:
 P18-1051.Poster.pdf