Semi-supervised Text Style Transfer: Cross Projection in Latent Space
This addresses the data scarcity issue in text style transfer, particularly for low-resource language pairs like ancient and modern Chinese, though it is incremental as it builds on existing semi-supervised approaches.
The authors tackled the problem of text style transfer with limited parallel data by proposing a semi-supervised model that uses both parallel and nonparallel data, achieving competitive results on a new dataset for ancient-modern Chinese style transfer.
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.