Semi-supervised Text Style Transfer: Cross Projection in Latent Space

by   Mingyue Shang, et al.

Text style transfer task requires the model to transfer a sentence of one style to another style while retaining its original content meaning, which is a challenging problem that has long suffered from the shortage of parallel data. In this paper, we first propose a semi-supervised text style transfer model that combines the small-scale parallel data with the large-scale nonparallel data. With these two types of training data, we introduce a projection function between the latent space of different styles and design two constraints to train it. We also introduce two other simple but effective semi-supervised methods to compare with. To evaluate the performance of the proposed methods, we build and release a novel style transfer dataset that alters sentences between the style of ancient Chinese poem and the modern Chinese.


page 1

page 2

page 3

page 4


Multiple Style Transfer via Variational AutoEncoder

Modern works on style transfer focus on transferring style from a single...

Semi-Supervised Formality Style Transfer with Consistency Training

Formality style transfer (FST) is a task that involves paraphrasing an i...

Learning from Bootstrapping and Stepwise Reinforcement Reward: A Semi-Supervised Framework for Text Style Transfer

Text style transfer is an important task in controllable language genera...

Semi-supervised Formality Style Transfer using Language Model Discriminator and Mutual Information Maximization

Formality style transfer is the task of converting informal sentences to...

Large-scale Hierarchical Alignment for Author Style Transfer

We propose a simple method for extracting pseudo-parallel monolingual se...

Structuring Latent Spaces for Stylized Response Generation

Generating responses in a targeted style is a useful yet challenging tas...