ParaGuide: Guided Diffusion Paraphrasers for Plug-and-Play Textual Style Transfer

TL;DR

ParaGuide introduces a flexible diffusion-based framework for text style transfer that adapts to arbitrary styles at inference, outperforming existing methods in various style transfer tasks.

Contribution

It presents a novel, parameter-efficient diffusion model that uses gradient guidance for versatile style transfer without extensive labeled data.

Findings

Outperforms strong baselines on formality, sentiment, and authorship transfer

Works effectively with limited labeled data and arbitrary styles

Validated through human and automatic evaluations

Abstract

Textual style transfer is the task of transforming stylistic properties of text while preserving meaning. Target "styles" can be defined in numerous ways, ranging from single attributes (e.g, formality) to authorship (e.g, Shakespeare). Previous unsupervised style-transfer approaches generally rely on significant amounts of labeled data for only a fixed set of styles or require large language models. In contrast, we introduce a novel diffusion-based framework for general-purpose style transfer that can be flexibly adapted to arbitrary target styles at inference time. Our parameter-efficient approach, ParaGuide, leverages paraphrase-conditioned diffusion models alongside gradient-based guidance from both off-the-shelf classifiers and strong existing style embedders to transform the style of text while preserving semantic information. We validate the method on the Enron Email Corpus, with both human and automatic evaluations, and find that it outperforms strong baselines on formality, sentiment, and even authorship style transfer.