Paraphrasing in Affirmative Terms Improves Negation Understanding

MohammadHossein Rezaei, Eduardo Blanco


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.
Anthology ID:
2024.acl-short.55
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
602–615
Language:
URL:
https://aclanthology.org/2024.acl-short.55
DOI:
10.18653/v1/2024.acl-short.55
Bibkey:
Cite (ACL):
MohammadHossein Rezaei and Eduardo Blanco. 2024. Paraphrasing in Affirmative Terms Improves Negation Understanding. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 602–615, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Paraphrasing in Affirmative Terms Improves Negation Understanding (Rezaei & Blanco, ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2024.acl-short.55.pdf