ST: Small-data Text Style Transfer via Multi-task Meta-Learning
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.
9 pages, 11 figures
References in corpus (11)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Convolutional Neural Networks for Sentence Classification
- Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach
- Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer
- A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer
- Yelp Dataset Challenge: Review Rating Prediction
- Domain Adaptive Dialog Generation via Meta Learning
- "Mask and Infill" : Applying Masked Language Model to Sentiment Transfer
- SHAPED: Shared-Private Encoder-Decoder for Text Style Adaptation
- A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer