Paraphrasing in Affirmative Terms Improves Negation Understanding

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Rezaei, MohammadHossein, Blanco, Eduardo
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911913735094272
author Rezaei, MohammadHossein
Blanco, Eduardo
author_facet Rezaei, MohammadHossein
Blanco, Eduardo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_07492
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Paraphrasing in Affirmative Terms Improves Negation Understanding
Rezaei, MohammadHossein
Blanco, Eduardo
Computation and Language
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.
title Paraphrasing in Affirmative Terms Improves Negation Understanding
topic Computation and Language
url https://arxiv.org/abs/2406.07492