Leveraging Affirmative Interpretations from Negation Improves Natural Language Understanding
This work addresses a specific problem in natural language understanding for AI models, offering an automated solution to improve handling of negation, but it is incremental as it builds on existing methods like T5 and RoBERTa.
The paper tackled the challenge of negation in natural language understanding by automatically collecting over 150,000 pairs of negated sentences and their affirmative interpretations, and showed that leveraging these pairs improves performance in tasks like natural language inference and sentiment analysis, with results including enhanced generation and classification.
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.