DeepAI AI Chat
Log In Sign Up

Interpretable Neural Predictions with Differentiable Binary Variables

05/20/2019
by   Joost Bastings, et al.
University of Amsterdam
0

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 rationale (i.e. a short and informative part of the input text), and a classifier that learns from the words in the rationale alone. Previous work proposed to assign binary latent masks to input positions and to promote short selections via sparsity-inducing penalties such as L0 regularisation. We propose a latent model that mixes discrete and continuous behaviour allowing at the same time for binary selections and gradient-based training without REINFORCE. In our formulation, we can tractably compute the expected value of penalties such as L0, which allows us to directly optimise the model towards a pre-specified text selection rate. We show that our approach is competitive with previous work on rationale extraction, and explore further uses in attention mechanisms.

READ FULL TEXT
10/01/2020

Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers

To build an interpretable neural text classifier, most of the prior work...
09/09/2021

SPECTRA: Sparse Structured Text Rationalization

Selective rationalization aims to produce decisions along with rationale...
11/10/2020

DoLFIn: Distributions over Latent Features for Interpretability

Interpreting the inner workings of neural models is a key step in ensuri...
12/05/2018

Training Competitive Binary Neural Networks from Scratch

Convolutional neural networks have achieved astonishing results in diffe...
06/11/2020

Latent Transformations for Discrete-Data Normalising Flows

Normalising flows (NFs) for discrete data are challenging because parame...
02/07/2023

Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

The strength of modern generative models lies in their ability to be con...
09/25/2019

Multi-Dimensional Explanation of Reviews

Neural models achieved considerable improvement for many natural languag...