Abstract
Unsupervised text style transfer is a challenging task that aims to alter the stylistic attributes of a given text without affecting its original content. One of the methods to achieve this is controllable style transfer, which allows for the control of the degree of style transfer. However, an issue encountered with controllable style transfer is the instability of transferred text fluency when the degree of the style transfer changes. To address this problem, we propose a novel approach that incorporates additional syntax parsing information during style transfer. By leveraging the syntactic information, our model is guided to generate natural sentences that effectively reflect the desired style while maintaining fluency. Experimental results show that our method achieves robust performance and improved fluency compared to previous controllable style transfer methods.- Anthology ID:
- 2023.wassa-1.15
- Volume:
- Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Jeremy Barnes, Orphée De Clercq, Roman Klinger
- Venue:
- WASSA
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 162–171
- Language:
- URL:
- https://aclanthology.org/2023.wassa-1.15
- DOI:
- 10.18653/v1/2023.wassa-1.15
- Cite (ACL):
- Ji-Eun Han and Kyung-Ah Sohn. 2023. Fluency Matters! Controllable Style Transfer with Syntax Guidance. In Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, pages 162–171, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Fluency Matters! Controllable Style Transfer with Syntax Guidance (Han & Sohn, WASSA 2023)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2023.wassa-1.15.pdf