EBBE-Text: Visualization of neural networks decision boundary
in automatic text classification

An original approach to explanation and interpretability

Learn more about our project

Our project !

Abstract

In text classification, many recent works deal with the interpretation of neural networks by producing explanations of predictions. The original approach presented in this paper consists in visualizing the decision boundary and the positioning of our data with respect to it, thus offering a new approach to explanation.

Our method first computes a sentence representation space and then exploits its linear structure in order to visualize the distribution and clustering of data around the decision boundary. The main contribution of our method is the decision boundary visualization process, allowing to explore the distance to the decision boundary (and thus the certainty of a network in its predictions) but also the paths leading to it or the proximity between sentences.

Click on images :

Here is a demo:

That's our team !

100x100

Delaforge Alexis

PhD Student

100x100

Sandra Bringay

Professor

100x100

Caroline Mollevi

Researcher

100x100

Jérôme Azé

Professor

100x100

Maximilien Servajean

Assistant Professor

100x100

Arnaud Sallaberry

Associate Professor

Financement