Empowering Language Understanding with Counterfactual Reasoning

TL;DR

This paper introduces a Counterfactual Reasoning Model that enhances language understanding by generating and comparing counterfactual samples, mimicking human counterfactual thinking to improve model robustness.

Contribution

It proposes a novel framework with generation and retrospective modules to incorporate counterfactual reasoning into language understanding models.

Findings

Improves sentiment analysis accuracy

Enhances natural language inference performance

Validates effectiveness through extensive experiments

Abstract

Present language understanding methods have demonstrated extraordinary ability of recognizing patterns in texts via machine learning. However, existing methods indiscriminately use the recognized patterns in the testing phase that is inherently different from us humans who have counterfactual thinking, e.g., to scrutinize for the hard testing samples. Inspired by this, we propose a Counterfactual Reasoning Model, which mimics the counterfactual thinking by learning from few counterfactual samples. In particular, we devise a generation module to generate representative counterfactual samples for each factual sample, and a retrospective module to retrospect the model prediction by comparing the counterfactual and factual samples. Extensive experiments on sentiment analysis (SA) and natural language inference (NLI) validate the effectiveness of our method.