# Unsupervised Text Style Transfer with Padded Masked Language Models

arXiv: https://arxiv.org/abs/2010.01054 · HTML: https://mlsanity.com/paper/2010.01054/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2020.

## Built on by (most cited first, 4 of 4)

- [Phrase-level Textual Adversarial Attack with Label Preservation](https://mlsanity.com/paper/2205.10710/) (2022)
- [Text Revision by On-the-Fly Representation Optimization](https://mlsanity.com/paper/2204.07359/) (2022)
- [Token-Modification Adversarial Attacks for Natural Language Processing: A Survey](https://mlsanity.com/paper/2103.00676/) (2021)
- [From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey](https://mlsanity.com/paper/2110.15871/) (2021)

## Abstract (arXiv)

We propose Masker, an unsupervised text-editing method for style transfer. To tackle cases when no parallel source-target pairs are available, we train masked language models (MLMs) for both the source and the target domain. Then we find the text spans where the two models disagree the most in terms of likelihood. This allows us to identify the source tokens to delete to transform the source text to match the style of the target domain. The deleted tokens are replaced with the target MLM, and by using a padded MLM variant, we avoid having to predetermine the number of inserted tokens. Our experiments on sentence fusion and sentiment transfer demonstrate that Masker performs competitively in a fully unsupervised setting. Moreover, in low-resource settings, it improves supervised methods' accuracy by over 10 percentage points when pre-training them on silver training data generated by Masker.