Interpretable Neural Predictions with Differentiable Binary Variables

Wilker Aziz
Wilker Aziz

Meeting of the Association for Computational Linguistics, 2019.

Cited by: 18|Views33
EI

Abstract:

The success of neural networks comes hand in hand with a desire for more interpretability. We focus on text classifiers and make them more interpretable by having them provide a justification, a rationale, for their predictions. We approach this problem by jointly training two neural network models: a latent model that selects a rationa...More

Code:

Data:

Your rating :
0

 

Tags
Comments