TY - GEN
T1 - Paraphrasing in Affirmative Terms Improves Negation Understanding
AU - Rezaei, Mohammad Hossein
AU - Blanco, Eduardo
N1 - Publisher Copyright:
© 2024 Association for Computational Linguistics.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85203844198
UR - https://www.scopus.com/pages/publications/85203844198#tab=citedBy
U2 - 10.18653/v1/2024.acl-short.55
DO - 10.18653/v1/2024.acl-short.55
M3 - Conference contribution
AN - SCOPUS:85203844198
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 602
EP - 615
BT - Short Papers
A2 - Ku, Lun-Wei
A2 - Martins, Andre F. T.
A2 - Srikumar, Vivek
PB - Association for Computational Linguistics (ACL)
T2 - 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024
Y2 - 11 August 2024 through 16 August 2024
ER -