StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer
Kangchen Zhu, Zhiliang Tian, Jingyu Wei, Ruifeng Luo, Yiping Song, Xiaoguang Mao
Abstract
Unsupervised text style transfer aims to modify the style of a sentence while preserving its content without parallel corpora. Existing approaches attempt to separate content from style, but some words contain both content and style information. It makes them difficult to disentangle, where unsatisfactory disentanglement results in the loss of the content information or the target style. To address this issue, researchers adopted a “cycle reconstruction” mechanism to maintain content information, but it is still hard to achieve satisfactory content preservation due to incomplete disentanglement. In this paper, we propose a new disentanglement-based method, StyleFlow, which effectively avoids the loss of contents through a better cycle reconstruction via a reversible encoder. The reversible encoder is a normalizing flow that can not only produce output given input but also infer the exact input given the output reversely. We design a stack of attention-aware coupling layers, where each layer is reversible and adopts the attention mechanism to improve the content-style disentanglement. Moreover, we propose a data augmentation method based on normalizing flow to enhance the training data. Our experiments on sentiment transfer and formality transfer tasks show that StyleFlow outperforms strong baselines on both content preservation and style transfer.- Anthology ID:
- 2024.lrec-main.1336
- Volume:
- Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
- Venues:
- LREC | COLING
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 15384–15397
- Language:
- URL:
- https://aclanthology.org/2024.lrec-main.1336
- DOI:
- Cite (ACL):
- Kangchen Zhu, Zhiliang Tian, Jingyu Wei, Ruifeng Luo, Yiping Song, and Xiaoguang Mao. 2024. StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 15384–15397, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer (Zhu et al., LREC-COLING 2024)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2024.lrec-main.1336.pdf