From text saliency to linguistic objects
Learning linguistic interpretable markers with a multi-channels convolutional architecture
Bibliographic Data
| ID | 19528985 |
|---|---|
| Authors | Laurent Vanni (Centre National de la Recherche Scientifique), Marco Corneli (0000-0002-9361-0080, Centre National de la Recherche Scientifique), Damon Mayaffre (0000-0003-0792-5973, Centre National de la Recherche Scientifique), Frédéric Precioso (0000-0001-8712-1443, Centre National de la Recherche Scientifique) |
| Year | 2023 |
| Volume | 24 |
| Publication date | 2023-01-01 |
| Peer Reviewed | Yes |
| Open Access | No |
| Type | ARTICLE |
| Venue | Corpus (JOURNAL) |
| Journal identifiers | ISSN: 1638-9808 • E-ISSN: 1765-3126 |
| Publisher | OpenEdition (PUBLISHER) |
| DOI | 10.4000/corpus.7667 |
| OpenAlex | W3015213360 |
| Language | EN |
| Citations received | 4 |
| References cited | 20 |
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
Convolutional neural network · Deconvolution · Machine learning · Natural language processing · Syntax · Visualization · Computational and Text Analysis Methods · Computer Science · Natural Language Processing Techniques · Topic Modeling · Artificial Intelligence
| Unique citing works | 4 |
|---|---|
| Citations per year | 0,67 |
| Citation span | 2020 - 2025 (6) |
| Citation velocity | recent |
| Highly cited | No |
| Citation types | Neutral: 4 |