DeepAI AI Chat
Log In Sign Up

StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer

by   Kangchen Zhu, et al.

Text style transfer aims to alter the style of a sentence while preserving its content. Due to the lack of parallel corpora, most recent work focuses on unsupervised methods and often uses cycle construction to train models. Since cycle construction helps to improve the style transfer ability of the model by rebuilding transferred sentences back to original-style sentences, it brings about a content loss in unsupervised text style transfer tasks. In this paper, we propose a novel disentanglement-based style transfer model StyleFlow to enhance content preservation. Instead of the typical encoder-decoder scheme, StyleFlow can not only conduct the forward process to obtain the output, but also infer to the input through the output. We design an attention-aware coupling layers to disentangle the content representations and the style representations of a sentence. Besides, we propose a data augmentation method based on Normalizing Flow to improve the robustness of the model. Experiment results demonstrate that our model preserves content effectively and achieves the state-of-the-art performance on the most metrics.


page 1

page 2

page 3

page 4


Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer

Unsupervised text style transfer is full of challenges due to the lack o...

Exploring Contextual Word-level Style Relevance for Unsupervised Style Transfer

Unsupervised style transfer aims to change the style of an input sentenc...

GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer

Non-parallel text style transfer has attracted increasing research inter...

Style Transfer from Non-Parallel Text by Cross-Alignment

This paper focuses on style transfer on the basis of non-parallel text. ...

Syntax Matters! Syntax-Controlled in Text Style Transfer

Existing text style transfer (TST) methods rely on style classifiers to ...

Language Style Transfer from Sentences with Arbitrary Unknown Styles

Language style transfer is the problem of migrating the content of a sou...

Parallel Data Augmentation for Formality Style Transfer

The main barrier to progress in the task of Formality Style Transfer is ...