Deep Learning for Text Style Transfer: A Survey

TL;DR

This survey reviews recent advances in neural text style transfer, covering methodologies, datasets, evaluation metrics, and future directions, highlighting the progress made since 2017 in controlling text attributes like politeness and emotion.

Contribution

It systematically summarizes over 100 studies on neural text style transfer, providing a comprehensive overview of methods, datasets, and evaluation approaches in the field.

Findings

Neural models have significantly improved style transfer quality.

Diverse datasets and evaluation metrics are used across studies.

Future research directions include better evaluation and handling of parallel data.

Abstract

Text style transfer is an important task in natural language generation, which aims to control certain attributes in the generated text, such as politeness, emotion, humor, and many others. It has a long history in the field of natural language processing, and recently has re-gained significant attention thanks to the promising performance brought by deep neural models. In this paper, we present a systematic survey of the research on neural text style transfer, spanning over 100 representative articles since the first neural text style transfer work in 2017. We discuss the task formulation, existing datasets and subtasks, evaluation, as well as the rich methodologies in the presence of parallel and non-parallel data. We also provide discussions on a variety of important topics regarding the future development of this task. Our curated paper list is at https://github.com/zhijing-jin/Text_Style_Transfer_Survey