Text Style Transfer via Optimal Transport

Nasim Nouri


Abstract
Text style transfer (TST) is a well-known task whose goal is to convert the style of the text (e.g., from formal to informal) while preserving its content. Recently, it has been shown that both syntactic and semantic similarities between the source and the converted text are important for TST. However, the interaction between these two concepts has not been modeled. In this work, we propose a novel method based on Optimal Transport for TST to simultaneously incorporate syntactic and semantic information into similarity computation between the source and the converted text. We evaluate the proposed method in both supervised and unsupervised settings. Our analysis reveal the superiority of the proposed model in both settings.
Anthology ID:
2022.naacl-main.182
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2532–2541
Language:
URL:
https://aclanthology.org/2022.naacl-main.182
DOI:
10.18653/v1/2022.naacl-main.182
Bibkey:
Cite (ACL):
Nasim Nouri. 2022. Text Style Transfer via Optimal Transport. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2532–2541, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Text Style Transfer via Optimal Transport (Nouri, NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.182.pdf
Software:
 2022.naacl-main.182.software.zip
Video:
 https://aclanthology.org/2022.naacl-main.182.mp4
Data
GYAFC