Disentangled Representation Learning for Non-Parallel Text Style Transfer
TL
TL;DR
A simple yet effective approach is proposed, which incorporates auxiliary multi-task and adversarial objectives, for style prediction and bag-of-words prediction, respectively, and this disentangled latent representation learning can be applied to style transfer on non-parallel corpora.
Abstract
This paper tackles the problem of disentangling the latent representations of style and content in language models. We propose a simple yet effective approach, which incorporates auxiliary multi-task and adversarial objectives, for style prediction and bag-of-words prediction, respectively. We show, both qualitatively and quantitatively, that the style and content are indeed disentangled in the latent space. This disentangled latent representation learning can be applied to style transfer on non-parallel corpora. We achieve high performance in terms of transfer accuracy, content preservation, and language fluency, in comparison to various previous approaches.
References49 items
1
Generating Sentences from Disentangled Syntactic and Semantic Spaces
2
Content preserving text generation with attribute controls
3
Probabilistic Natural Language Generation with Wasserstein Autoencoders
4
Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach
5