Text Style Transfer: Leveraging a Style Classifier on Entangled Latent Representations

Xiaoyan Li, Sun Sun, Yunli Wang


Abstract
Learning a good latent representation is essential for text style transfer, which generates a new sentence by changing the attributes of a given sentence while preserving its content. Most previous works adopt disentangled latent representation learning to realize style transfer. We propose a novel text style transfer algorithm with entangled latent representation, and introduce a style classifier that can regulate the latent structure and transfer style. Moreover, our algorithm for style transfer applies to both single-attribute and multi-attribute transfer. Extensive experimental results show that our method generally outperforms state-of-the-art approaches.
Anthology ID:
2021.repl4nlp-1.9
Volume:
Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)
Month:
August
Year:
2021
Address:
Online
Editors:
Anna Rogers, Iacer Calixto, Ivan Vulić, Naomi Saphra, Nora Kassner, Oana-Maria Camburu, Trapit Bansal, Vered Shwartz
Venue:
RepL4NLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
72–82
Language:
URL:
https://aclanthology.org/2021.repl4nlp-1.9
DOI:
10.18653/v1/2021.repl4nlp-1.9
Bibkey:
Cite (ACL):
Xiaoyan Li, Sun Sun, and Yunli Wang. 2021. Text Style Transfer: Leveraging a Style Classifier on Entangled Latent Representations. In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), pages 72–82, Online. Association for Computational Linguistics.
Cite (Informal):
Text Style Transfer: Leveraging a Style Classifier on Entangled Latent Representations (Li et al., RepL4NLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2021.repl4nlp-1.9.pdf