Paraphrase Identification via Textual Inference

Ning Shi, Bradley Hauer, Jai Riley, Grzegorz Kondrak


Abstract
Paraphrase identification (PI) and natural language inference (NLI) are two important tasks in natural language processing. Despite their distinct objectives, an underlying connection exists, which has been notably under-explored in empirical investigations. We formalize the relationship between these semantic tasks and introduce a method for solving PI using an NLI system, including the adaptation of PI datasets for fine-tuning NLI models. Through extensive evaluations on six PI benchmarks, across both zero-shot and fine-tuned settings, we showcase the efficacy of NLI models for PI through our proposed reduction. Remarkably, our fine-tuning procedure enables NLI models to outperform dedicated PI models on PI datasets. In addition, our findings provide insights into the limitations of current PI benchmarks.
Anthology ID:
2024.starsem-1.11
Volume:
Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Danushka Bollegala, Vered Shwartz
Venue:
*SEM
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
133–141
Language:
URL:
https://aclanthology.org/2024.starsem-1.11
DOI:
10.18653/v1/2024.starsem-1.11
Bibkey:
Cite (ACL):
Ning Shi, Bradley Hauer, Jai Riley, and Grzegorz Kondrak. 2024. Paraphrase Identification via Textual Inference. In Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024), pages 133–141, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Paraphrase Identification via Textual Inference (Shi et al., *SEM 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.starsem-1.11.pdf