# CUT: Controllable Unsupervised Text Simplification

arXiv: https://arxiv.org/abs/2012.01936 · HTML: https://mlsanity.com/paper/2012.01936/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 3 of 3)

- [Med-EASi: Finely Annotated Dataset and Models for Controllable Simplification of Medical Texts](https://mlsanity.com/paper/2302.09155/) (2023)
- [Unsupervised Sentence Simplification via Dependency Parsing](https://mlsanity.com/paper/2206.12261/) (2022)
- [SimCSum: Joint Learning of Simplification and Cross-lingual Summarization for Cross-lingual Science Journalism](https://mlsanity.com/paper/2304.01621/) (2023)

## Abstract (arXiv)

In this paper, we focus on the challenge of learning controllable text simplifications in unsupervised settings. While this problem has been previously discussed for supervised learning algorithms, the literature on the analogies in unsupervised methods is scarse. We propose two unsupervised mechanisms for controlling the output complexity of the generated texts, namely, back translation with control tokens (a learning-based approach) and simplicity-aware beam search (decoding-based approach). We show that by nudging a back-translation algorithm to understand the relative simplicity of a text in comparison to its noisy translation, the algorithm self-supervises itself to produce the output of the desired complexity. This approach achieves competitive performance on well-established benchmarks: SARI score of 46.88% and FKGL of 3.65% on the Newsela dataset.