# Multiple-Attribute Text Style Transfer

arXiv: https://arxiv.org/abs/1811.00552 · HTML: https://mlsanity.com/paper/1811.00552/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2018.

## Built on by (most cited first, 20 of 20)

- [Controlled Text Generation as Continuous Optimization with Multiple Constraints](https://mlsanity.com/paper/2108.01850/) (2021)
- [XFORMAL: A Benchmark for Multilingual Formality Style Transfer](https://mlsanity.com/paper/2104.04108/) (2021)
- [Meet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few Utterances](https://mlsanity.com/paper/2204.10825/) (2022)
- [Text Style Transfer for Bias Mitigation using Masked Language Modeling](https://mlsanity.com/paper/2201.08643/) (2022)
- [Neural Data-to-Text Generation with LM-based Text Augmentation](https://mlsanity.com/paper/2102.03556/) (2021)
- [Few-shot Controllable Style Transfer for Low-Resource Multilingual Settings](https://mlsanity.com/paper/2110.07385/) (2021)
- [Med-EASi: Finely Annotated Dataset and Models for Controllable Simplification of Medical Texts](https://mlsanity.com/paper/2302.09155/) (2023)
- [MOVER: Mask, Over-generate and Rank for Hyperbole Generation](https://mlsanity.com/paper/2109.07726/) (2021)
- [Political Depolarization of News Articles Using Attribute-aware Word Embeddings](https://mlsanity.com/paper/2101.01391/) (2021)
- [On Fairness of Low-Rank Adaptation of Large Models](https://mlsanity.com/paper/2405.17512/) (2024)
- [So Different Yet So Alike! Constrained Unsupervised Text Style Transfer](https://mlsanity.com/paper/2205.04093/) (2022)
- [T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation](https://mlsanity.com/paper/2212.01667/) (2022)
- [DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting](https://mlsanity.com/paper/2101.11836/) (2021)
- [From Solving a Problem Boldly to Cutting the Gordian Knot: Idiomatic Text Generation](https://mlsanity.com/paper/2104.06541/) (2021)
- [Steering Large Language Models with Register Analysis for Arbitrary Style Transfer](https://mlsanity.com/paper/2505.00679/) (2025)
- [Conversation Style Transfer using Few-Shot Learning](https://mlsanity.com/paper/2302.08362/) (2023)
- [CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogs](https://mlsanity.com/paper/2311.17376/) (2023)
- [Balancing Effect of Training Dataset Distribution of Multiple Styles for Multi-Style Text Transfer](https://mlsanity.com/paper/2305.15582/) (2023)
- [BERT Goes Off-Topic: Investigating the Domain Transfer Challenge using Genre Classification](https://mlsanity.com/paper/2311.16083/) (2023)
- [RT-SFT: Text Style Transfer from Non-Parallel Corpora by Roundtrip Translation](https://mlsanity.com/paper/2602.15013/) (2026)

## Abstract (arXiv)

The dominant approach to unsupervised "style transfer" in text is based on the idea of learning a latent representation, which is independent of the attributes specifying its "style". In this paper, we show that this condition is not necessary and is not always met in practice, even with domain adversarial training that explicitly aims at learning such disentangled representations. We thus propose a new model that controls several factors of variation in textual data where this condition on disentanglement is replaced with a simpler mechanism based on back-translation. Our method allows control over multiple attributes, like gender, sentiment, product type, etc., and a more fine-grained control on the trade-off between content preservation and change of style with a pooling operator in the latent space. Our experiments demonstrate that the fully entangled model produces better generations, even when tested on new and more challenging benchmarks comprising reviews with multiple sentences and multiple attributes.