# Stable Style Transformer: Delete and Generate Approach with Encoder-Decoder for Text Style Transfer

arXiv: https://arxiv.org/abs/2005.12086 · HTML: https://mlsanity.com/paper/2005.12086/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2020.

## Built on by (most cited first, 22 of 22)

- [Text Detoxification using Large Pre-trained Neural Models](https://mlsanity.com/paper/2109.08914/) (2021)
- [You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content](https://mlsanity.com/paper/2308.05596/) (2023)
- [Human Evaluation of Creative NLG Systems: An Interdisciplinary Survey on Recent Papers](https://mlsanity.com/paper/2108.00308/) (2021)
- [A Review of Text Style Transfer using Deep Learning](https://mlsanity.com/paper/2109.15144/) (2021)
- [A Call for Standardization and Validation of Text Style Transfer Evaluation](https://mlsanity.com/paper/2306.00539/) (2023)
- [Multidimensional Evaluation for Text Style Transfer Using ChatGPT](https://mlsanity.com/paper/2304.13462/) (2023)
- [Generic resources are what you need: Style transfer tasks without task-specific parallel training data](https://mlsanity.com/paper/2109.04543/) (2021)
- [DiffuDetox: A Mixed Diffusion Model for Text Detoxification](https://mlsanity.com/paper/2306.08505/) (2023)
- [Prefix-Tuning Based Unsupervised Text Style Transfer](https://mlsanity.com/paper/2310.14599/) (2023)
- [From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey](https://mlsanity.com/paper/2110.15871/) (2021)
- [Human-Guided Fair Classification for Natural Language Processing](https://mlsanity.com/paper/2212.10154/) (2022)
- [StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2212.09670/) (2022)
- [Learning from Response not Preference: A Stackelberg Approach for LLM Detoxification using Non-parallel Data](https://mlsanity.com/paper/2410.20298/) (2024)
- [GPT-DETOX: An In-Context Learning-Based Paraphraser for Text Detoxification](https://mlsanity.com/paper/2404.03052/) (2024)
- [K/DA: Automated Data Generation Pipeline for Detoxifying Implicitly Offensive Language in Korean](https://mlsanity.com/paper/2506.13513/) (2025)
- [Transforming Multi-Conditioned Generation from Meaning Representation](https://mlsanity.com/paper/2101.04257/) (2021)
- [Gradient-guided Unsupervised Text Style Transfer via Contrastive Learning](https://mlsanity.com/paper/2202.00469/) (2022)
- [JieHua Paintings Style Feature Extracting Model using Stable Diffusion with ControlNet](https://mlsanity.com/paper/2408.11744/) (2024)
- [Unsupervised Text Style Transfer for Controllable Intensity](https://mlsanity.com/paper/2601.01060/) (2026)
- [On Text Style Transfer via Style Masked Language Models](https://mlsanity.com/paper/2210.06394/) (2022)
- [Generative Sentiment Transfer via Adaptive Masking](https://mlsanity.com/paper/2302.12045/) (2023)
- [Generation, Evaluation, and Explanation of Novelists' Styles with Single-Token Prompts](https://mlsanity.com/paper/2511.20459/) (2025)

## Abstract (arXiv)

Text style transfer is the task that generates a sentence by preserving the content of the input sentence and transferring the style. Most existing studies are progressing on non-parallel datasets because parallel datasets are limited and hard to construct. In this work, we introduce a method that follows two stages in non-parallel datasets. The first stage is to delete attribute markers of a sentence directly through a classifier. The second stage is to generate a transferred sentence by combining the content tokens and the target style. We experiment on two benchmark datasets and evaluate context, style, fluency, and semantic. It is difficult to select the best system using only these automatic metrics, but it is possible to select stable systems. We consider only robust systems in all automatic evaluation metrics to be the minimum conditions that can be used in real applications. Many previous systems are difficult to use in certain situations because performance is significantly lower in several evaluation metrics. However, our system is stable in all automatic evaluation metrics and has results comparable to other models. Also, we compare the performance results of our system and the unstable system through human evaluation. Our code and data are available at the link (https://github.com/rungjoo/Stable-Style-Transformer).