ST²: Small-data Text Style Transfer via Multi-task Meta-Learning

2020/04/24 by Chen, Xiwen, Zhu, Kenny Q.
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2004.11742

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.

Related

• Multi-Pair Text Style Transfer on Unbalanced Data
• Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models
• Semi-supervised Text Style Transfer: Cross Projection in Latent Space
• Learning to Generate Multiple Style Transfer Outputs for an Input Sentence
• TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restyling