English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Text style transfer aims to alter the style of a sentence while preservingits content. Due to the lack of parallel corpora, most recent work focuses onunsupervised methods and often uses cycle construction to train models. Sincecycle construction helps to improve the style transfer ability of the model byrebuilding transferred sentences back to original-style sentences, it bringsabout a content loss in unsupervised text style transfer tasks. In this paper,we propose a novel disentanglement-based style transfer model StyleFlow toenhance content preservation. Instead of the typical encoder-decoder scheme,StyleFlow can not only conduct the forward process to obtain the output, butalso infer to the input through the output. We design an attention-awarecoupling layers to disentangle the content representations and the stylerepresentations of a sentence. Besides, we propose a data augmentation methodbased on Normalizing Flow to improve the robustness of the model. Experimentresults demonstrate that our model preserves content effectively and achievesthe state-of-the-art performance on the most metrics.

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