Few-shot Controllable Style Transfer for Low-Resource Multilingual Settings

TL;DR

This paper introduces a new method for few-shot style transfer in low-resource multilingual settings, significantly improving performance over prior approaches and enabling controllable style transfer without retraining.

Contribution

The authors propose a novel approach modeling stylistic differences between paraphrases, achieving 2-3x better results in multiple languages and enabling style control without retraining.

Findings

Achieved 2-3x improvement in formality transfer accuracy.

Enabled controllable style transfer with an input scalar knob.

Crowdsourced datasets for evaluation in low-resource languages.

Abstract

Style transfer is the task of rewriting a sentence into a target style while approximately preserving content. While most prior literature assumes access to a large style-labelled corpus, recent work (Riley et al. 2021) has attempted "few-shot" style transfer using only 3-10 sentences at inference for style extraction. In this work we study a relevant low-resource setting: style transfer for languages where no style-labelled corpora are available. We notice that existing few-shot methods perform this task poorly, often copying inputs verbatim. We push the state-of-the-art for few-shot style transfer with a new method modeling the stylistic difference between paraphrases. When compared to prior work, our model achieves 2-3x better performance in formality transfer and code-mixing addition across seven languages. Moreover, our method is better at controlling the style transfer magnitude using an input scalar knob. We report promising qualitative results for several attribute transfer tasks (sentiment transfer, simplification, gender neutralization, text anonymization) all without retraining the model. Finally, we find model evaluation to be difficult due to the lack of datasets and metrics for many languages. To facilitate future research we crowdsource formality annotations for 4000 sentence pairs in four Indic languages, and use this data to design our automatic evaluations.