Leveraging Affirmative Interpretations from Negation Improves Natural Language Understanding

TL;DR

This paper demonstrates that using automatically collected affirmative interpretations of negated sentences enhances natural language understanding tasks, including inference and sentiment analysis, without manual effort.

Contribution

It introduces an automated method to generate affirmative interpretations of negations and shows their effectiveness across multiple NLP tasks.

Findings

Improved performance in natural language inference tasks.

Enhanced sentiment analysis accuracy.

Automated approach reduces manual annotation effort.

Abstract

Negation poses a challenge in many natural language understanding tasks. Inspired by the fact that understanding a negated statement often requires humans to infer affirmative interpretations, in this paper we show that doing so benefits models for three natural language understanding tasks. We present an automated procedure to collect pairs of sentences with negation and their affirmative interpretations, resulting in over 150,000 pairs. Experimental results show that leveraging these pairs helps (a) T5 generate affirmative interpretations from negations in a previous benchmark, and (b) a RoBERTa-based classifier solve the task of natural language inference. We also leverage our pairs to build a plug-and-play neural generator that given a negated statement generates an affirmative interpretation. Then, we incorporate the pretrained generator into a RoBERTa-based classifier for sentiment analysis and show that doing so improves the results. Crucially, our proposal does not require any manual effort.