A Game Theoretic Approach to Class-wise Selective Rationalization

TL;DR

This paper introduces a game theoretic method for class-dependent rationalization in neural models, enabling the highlighting of evidence supporting both factual and counterfactual scenarios, improving interpretability.

Contribution

It presents a novel game theoretic framework for class-wise rationalization, capturing multi-faceted rationales and supporting both factual and counterfactual explanations.

Findings

Effectively identifies factual and counterfactual rationales

Aligns with human rationalization in sentiment tasks

Demonstrates improved interpretability

Abstract

Selection of input features such as relevant pieces of text has become a common technique of highlighting how complex neural predictors operate. The selection can be optimized post-hoc for trained models or incorporated directly into the method itself (self-explaining). However, an overall selection does not properly capture the multi-faceted nature of useful rationales such as pros and cons for decisions. To this end, we propose a new game theoretic approach to class-dependent rationalization, where the method is specifically trained to highlight evidence supporting alternative conclusions. Each class involves three players set up competitively to find evidence for factual and counterfactual scenarios. We show theoretically in a simplified scenario how the game drives the solution towards meaningful class-dependent rationales. We evaluate the method in single- and multi-aspect sentiment classification tasks and demonstrate that the proposed method is able to identify both factual (justifying the ground truth label) and counterfactual (countering the ground truth label) rationales consistent with human rationalization. The code for our method is publicly available.