ST${}^2$: Small-data Text Style Transfer via Multi-task Meta-Learning

Abstract

Text style transfer aims to paraphrase a sentence in one style into another style while preserving content. Due to lack of parallel training data, state-of-art methods are unsupervised and rely on large datasets that share content. Furthermore, existing methods have been applied on very limited categories of styles such as positive/negative and formal/informal. In this work, we develop a meta-learning framework to transfer between any kind of text styles, including personal writing styles that are more fine-grained, share less content and have much smaller training data. While state-of-art models fail in the few-shot style transfer task, our framework effectively utilizes information from other styles to improve both language fluency and style transfer accuracy.

9 pages, 11 figures

References in corpus (4)

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Convolutional Neural Networks for Sentence Classification
• A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer
• A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer