Rationalization through Concepts

05/11/2021
by   Diego Antognini, et al.
0

Automated predictions require explanations to be interpretable by humans. One type of explanation is a rationale, i.e., a selection of input features such as relevant text snippets from which the model computes the outcome. However, a single overall selection does not provide a complete explanation, e.g., weighing several aspects for decisions. To this end, we present a novel self-interpretable model called ConRAT. Inspired by how human explanations for high-level decisions are often based on key concepts, ConRAT extracts a set of text snippets as concepts and infers which ones are described in the document. Then, it explains the outcome with a linear aggregation of concepts. Two regularizers drive ConRAT to build interpretable concepts. In addition, we propose two techniques to boost the rationale and predictive performance further. Experiments on both single- and multi-aspect sentiment classification tasks show that ConRAT is the first to generate concepts that align with human rationalization while using only the overall label. Further, it outperforms state-of-the-art methods trained on each aspect label independently.

READ FULL TEXT

page 8

page 14

page 15

research
05/28/2019

EDUCE: Explaining model Decisions through Unsupervised Concepts Extraction

With the advent of deep neural networks, some research focuses towards u...
research
09/15/2017

Embedding Deep Networks into Visual Explanations

In this paper, we propose a novel explanation module to explain the pred...
research
08/25/2021

Inducing Semantic Grouping of Latent Concepts for Explanations: An Ante-Hoc Approach

Self-explainable deep models are devised to represent the hidden concept...
research
10/28/2019

A Game Theoretic Approach to Class-wise Selective Rationalization

Selection of input features such as relevant pieces of text has become a...
research
08/16/2020

Towards Faithful and Meaningful Interpretable Representations

Interpretable representations are the backbone of many black-box explain...
research
04/01/2022

Provable concept learning for interpretable predictions using variational inference

In safety critical applications, practitioners are reluctant to trust ne...
research
12/30/2022

Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces

Explainable AI transforms opaque decision strategies of ML models into e...

Please sign up or login with your details

Forgot password? Click here to reset