SC2: Towards Enhancing Content Preservation and Style Consistency in Long Text Style Transfer

Jie Zhao, Ziyu Guan, Cai Xu, Wei Zhao, Yue Jiang


Abstract
Text style transfer (TST) aims to vary the style polarity of text while preserving the semantic content. Although recent advancements have demonstrated remarkable progress in short TST, it remains a relatively straightforward task with limited practical applications. The more comprehensive long TST task presents two challenges: (1) existing methods encounter difficulties in accurately evaluating content attributes in multiple words, leading to content degradation; (2) the conventional vanilla style classifier loss encounters obstacles in maintaining consistent style across multiple generated sentences.In this paper, we propose a novel method SC2, where a multilayer Joint Style-Content Weighed (JSCW) module and a Style Consistency loss are designed to address the two issues. The JSCW simultaneously assesses the amounts of style and content attributes within a token, aiming to acquire a lossless content representation and thereby enhancing content preservation. The multiple JSCW layers further progressively refine content representations. We design a style consistency loss to ensure the generated multiple sentences consistently reflect the target style polarity. Moreover, we incorporate a denoising non-autoregressive decoder to accelerate the training. We conduct plentiful experiments and the results show significant improvements of SC2 over competitive baselines. Our code: https://github.com/jiezhao6/SC2.
Anthology ID:
2024.acl-long.535
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long 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:
9949–9960
Language:
URL:
https://aclanthology.org/2024.acl-long.535
DOI:
10.18653/v1/2024.acl-long.535
Bibkey:
Cite (ACL):
Jie Zhao, Ziyu Guan, Cai Xu, Wei Zhao, and Yue Jiang. 2024. SC2: Towards Enhancing Content Preservation and Style Consistency in Long Text Style Transfer. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9949–9960, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
SC2: Towards Enhancing Content Preservation and Style Consistency in Long Text Style Transfer (Zhao et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.535.pdf