ParaLS: Lexical Substitution via Pretrained Paraphraser

Jipeng Qiang, Kang Liu, Yun Li, Yunhao Yuan, Yi Zhu


Abstract
Lexical substitution (LS) aims at finding appropriate substitutes for a target word in a sentence. Recently, LS methods based on pretrained language models have made remarkable progress, generating potential substitutes for a target word through analysis of its contextual surroundings. However, these methods tend to overlook the preservation of the sentence’s meaning when generating the substitutes. This study explores how to generate the substitute candidates from a paraphraser, as the generated paraphrases from a paraphraser contain variations in word choice and preserve the sentence’s meaning. Since we cannot directly generate the substitutes via commonly used decoding strategies, we propose two simple decoding strategies that focus on the variations of the target word during decoding. Experimental results show that our methods outperform state-of-the-art LS methods based on pre-trained language models on three benchmarks.
Anthology ID:
2023.acl-long.206
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3731–3746
Language:
URL:
https://aclanthology.org/2023.acl-long.206
DOI:
10.18653/v1/2023.acl-long.206
Bibkey:
Cite (ACL):
Jipeng Qiang, Kang Liu, Yun Li, Yunhao Yuan, and Yi Zhu. 2023. ParaLS: Lexical Substitution via Pretrained Paraphraser. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3731–3746, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
ParaLS: Lexical Substitution via Pretrained Paraphraser (Qiang et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2023.acl-long.206.pdf
Video:
 https://preview.aclanthology.org/improve-issue-templates/2023.acl-long.206.mp4