SimpleStyle: An Adaptable Style Transfer Approach

TL;DR

SimpleStyle is a minimalist yet effective style transfer method using controlled denoising and output filtering, competitive with state-of-the-art approaches, applicable to real-world data, and introducing a novel soft noising technique.

Contribution

It presents a simple, adaptable style transfer approach with a new soft noising technique, demonstrating competitive performance and practical applicability beyond academic datasets.

Findings

Competitive with state-of-the-art methods in automatic and human evaluations.

Effective in transferring a wide range of real-world text attributes.

Enables training a student model for efficient style transfer.

Abstract

Attribute-controlled text rewriting, also known as text style-transfer, has a crucial role in regulating attributes and biases of textual training data and a machine generated text. In this work we present SimpleStyle, a minimalist yet effective approach for style-transfer composed of two simple ingredients: controlled denoising and output filtering. Despite the simplicity of our approach, which can be succinctly described with a few lines of code, it is competitive with previous state-of-the-art methods both in automatic and in human evaluation. To demonstrate the adaptability and practical value of our system beyond academic data, we apply SimpleStyle to transfer a wide range of text attributes appearing in real-world textual data from social networks. Additionally, we introduce a novel "soft noising" technique that further improves the performance of our system. We also show that teaching a student model to generate the output of SimpleStyle can result in a system that performs style transfer of equivalent quality with only a single greedy-decoded sample. Finally, we suggest our method as a remedy for the fundamental incompatible baseline issue that holds progress in the field. We offer our protocol as a simple yet strong baseline for works that wish to make incremental advancements in the field of attribute controlled text rewriting.