Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

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

Abstract : 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.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-03142170
Contributor : Marco Corneli <>
Submitted on : Monday, February 15, 2021 - 6:45:28 PM
Last modification on : Thursday, February 18, 2021 - 3:09:17 AM

File

wTDS_HAL.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03142170, version 1

Citation

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⟩

Share

Metrics

Record views

13

Files downloads

6