Deep Learning for Text Style Transfer: A Survey

By Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, Rada Mihalcea. 2020

303 citations recorded by the source corpus.

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 article, 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.1

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

A Recipe for Arbitrary Text Style Transfer with Large Language Models (2021, background): “Hence, recent survey papers have identiﬁed a need for new methods that both reduce the training data requirements and expand the scope of styles supported (Jin et al., 2020; Hu et al., 2020).”
Steering Language Models With Activation Engineering (2023, unknown): “…, as with guided or trainable decoding (Gu et al. 2017; Grover et al. 2019; see Zhang et al. 2022a for an overview of controlled generation and Jin et al. 2022 for textual style transfer); • Intervening on the prompt , as with automated prompt engineering (Shin et al. 2020; Zhou et al. 2022);…”
A Review of Human Evaluation for Style Transfer (2021, methodology): “Paper Selection We select papers for this study from the list compiled by Jin et al. (2021) who conduct a comprehensive review of ST that covers the task formulation; evaluation metrics; opinion papers and deep-learning based textual ST meth-ods.”
RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning (2022, methodology): “Experiments on TST exhibit similar patterns as shown in Figure 7 in Appendix §B.”
Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models (2022, background): “In doing so, we hope to help address the recent call-to-action on reproducibility in TST from Jin et al. (2021); they encouraged researchers to share their data and evaluation codes in order to establish reliable benchmarks and facilitate easier comparison of new studies with existing work.”
Evaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality Transfer (2021, methodology): “We select FoST for this work since it is one of the most frequently studied styles (Jin et al., 2020) and there is human annotated data including human references available for these evaluations (Rao and Tetreault, 2018; Briakou et al.”