# TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restyling

arXiv: https://arxiv.org/abs/2010.03802 · HTML: https://mlsanity.com/paper/2010.03802/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2020.

## Built on by (most cited first, 30 of 40)

- [In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering](https://mlsanity.com/paper/2311.06668/) (2023)
- [Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond](https://mlsanity.com/paper/2109.00725/) (2021)
- [RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting](https://mlsanity.com/paper/2305.15685/) (2023)
- [StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples](https://mlsanity.com/paper/2410.12757/) (2024)
- [Meet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few Utterances](https://mlsanity.com/paper/2204.10825/) (2022)
- [Learning Interpretable Style Embeddings via Prompting LLMs](https://mlsanity.com/paper/2305.12696/) (2023)
- [Few-shot Controllable Style Transfer for Low-Resource Multilingual Settings](https://mlsanity.com/paper/2110.07385/) (2021)
- [FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation](https://mlsanity.com/paper/2210.00193/) (2022)
- [ParaGuide: Guided Diffusion Paraphrasers for Plug-and-Play Textual Style Transfer](https://mlsanity.com/paper/2308.15459/) (2023)
- [TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings](https://mlsanity.com/paper/2406.15586/) (2024)
- [Prompt-Based Editing for Text Style Transfer](https://mlsanity.com/paper/2301.11997/) (2023)
- [Controlling Translation Formality Using Pre-trained Multilingual Language Models](https://mlsanity.com/paper/2205.06644/) (2022)
- [LLM-Friendly Knowledge Representation for Customer Support](https://mlsanity.com/paper/2510.10331/) (2025)
- [Non-Parallel Text Style Transfer with Self-Parallel Supervision](https://mlsanity.com/paper/2204.08123/) (2022)
- [Authorship Style Transfer with Policy Optimization](https://mlsanity.com/paper/2403.08043/) (2024)
- [Low-Resource Authorship Style Transfer: Can Non-Famous Authors Be Imitated?](https://mlsanity.com/paper/2212.08986/) (2022)
- [Learning to Generate Text in Arbitrary Writing Styles](https://mlsanity.com/paper/2312.17242/) (2023)
- [Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2205.02309/) (2022)
- [FAST: Improving Controllability for Text Generation with Feedback Aware Self-Training](https://mlsanity.com/paper/2210.03167/) (2022)
- [Towards an On-device Agent for Text Rewriting](https://mlsanity.com/paper/2308.11807/) (2023)
- [A Review of Human Emotion Synthesis Based on Generative Technology](https://mlsanity.com/paper/2412.07116/) (2024)
- [Augmenting Poetry Composition with Verse by Verse](https://mlsanity.com/paper/2103.17205/) (2021)
- [From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey](https://mlsanity.com/paper/2110.15871/) (2021)
- [Low Resource Style Transfer via Domain Adaptive Meta Learning](https://mlsanity.com/paper/2205.12475/) (2022)
- [Conversation Style Transfer using Few-Shot Learning](https://mlsanity.com/paper/2302.08362/) (2023)
- [Visual Captioning at Will: Describing Images and Videos Guided by a Few Stylized Sentences](https://mlsanity.com/paper/2307.16399/) (2023)
- [Proofread: Fixes All Errors with One Tap](https://mlsanity.com/paper/2406.04523/) (2024)
- [SC2: Towards Enhancing Content Preservation and Style Consistency in Long Text Style Transfer](https://mlsanity.com/paper/2406.04578/) (2024)
- [Style Transfer with Multi-iteration Preference Optimization](https://mlsanity.com/paper/2406.11581/) (2024)
- [Towards Style Alignment in Cross-Cultural Translation](https://mlsanity.com/paper/2507.00216/) (2025)

## Abstract (arXiv)

We present a novel approach to the problem of text style transfer. Unlike previous approaches requiring style-labeled training data, our method makes use of readily-available unlabeled text by relying on the implicit connection in style between adjacent sentences, and uses labeled data only at inference time. We adapt T5 (Raffel et al., 2020), a strong pretrained text-to-text model, to extract a style vector from text and use it to condition the decoder to perform style transfer. As our label-free training results in a style vector space encoding many facets of style, we recast transfers as "targeted restyling" vector operations that adjust specific attributes of the input while preserving others. We demonstrate that training on unlabeled Amazon reviews data results in a model that is competitive on sentiment transfer, even compared to models trained fully on labeled data. Furthermore, applying our novel method to a diverse corpus of unlabeled web text results in a single model capable of transferring along multiple dimensions of style (dialect, emotiveness, formality, politeness, sentiment) despite no additional training and using only a handful of exemplars at inference time.