Paraphrasing in Affirmative Terms Improves Negation Understanding

TL;DR

This paper explores how using affirmative paraphrases can enhance language models' understanding of negation, leading to improved performance across various natural language understanding tasks.

Contribution

It introduces an automatic method for generating affirmative interpretations to improve negation comprehension in language models.

Findings

Improved performance on CondaQA dataset.

Enhanced results across five NLU tasks.

Automatic affirmative paraphrasing boosts negation robustness.

Abstract

Negation is a common linguistic phenomenon. Yet language models face challenges with negation in many natural language understanding tasks such as question answering and natural language inference. In this paper, we experiment with seamless strategies that incorporate affirmative interpretations (i.e., paraphrases without negation) to make models more robust against negation. Crucially, our affirmative interpretations are obtained automatically. We show improvements with CondaQA, a large corpus requiring reasoning with negation, and five natural language understanding tasks.