# Controllable Sentence Simplification

arXiv: https://arxiv.org/abs/1910.02677 · HTML: https://mlsanity.com/paper/1910.02677/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2019.

## Built on by (most cited first, 30 of 78)

- [LENS: A Learnable Evaluation Metric for Text Simplification](https://mlsanity.com/paper/2212.09739/) (2022)
- [Keep it Simple: Unsupervised Simplification of Multi-Paragraph Text](https://mlsanity.com/paper/2107.03444/) (2021)
- [BLESS: Benchmarking Large Language Models on Sentence Simplification](https://mlsanity.com/paper/2310.15773/) (2023)
- [Evaluating Factuality in Text Simplification](https://mlsanity.com/paper/2204.07562/) (2022)
- [Towards Optimizing the Costs of LLM Usage](https://mlsanity.com/paper/2402.01742/) (2024)
- [Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts](https://mlsanity.com/paper/2307.02768/) (2023)
- [Text Simplification by Tagging](https://mlsanity.com/paper/2103.05070/) (2021)
- [Revisiting non-English Text Simplification: A Unified Multilingual Benchmark](https://mlsanity.com/paper/2305.15678/) (2023)
- [Generating Summaries with Controllable Readability Levels](https://mlsanity.com/paper/2310.10623/) (2023)
- [Natural Language Processing in the Patent Domain: A Survey](https://mlsanity.com/paper/2403.04105/) (2024)
- [Towards Process-Oriented, Modular, and Versatile Question Generation that Meets Educational Needs](https://mlsanity.com/paper/2205.00355/) (2022)
- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)
- [Multitasking Framework for Unsupervised Simple Definition Generation](https://mlsanity.com/paper/2203.12926/) (2022)
- [Rethinking Automatic Evaluation in Sentence Simplification](https://mlsanity.com/paper/2104.07560/) (2021)
- [Med-EASi: Finely Annotated Dataset and Models for Controllable Simplification of Medical Texts](https://mlsanity.com/paper/2302.09155/) (2023)
- [Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading Comprehension](https://mlsanity.com/paper/2312.10126/) (2023)
- [Sentence Simplification via Large Language Models](https://mlsanity.com/paper/2302.11957/) (2023)
- [Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSA](https://mlsanity.com/paper/2305.14458/) (2023)
- [An Unsupervised Method for Building Sentence Simplification Corpora in Multiple Languages](https://mlsanity.com/paper/2109.00165/) (2021)
- [Controlling Pre-trained Language Models for Grade-Specific Text Simplification](https://mlsanity.com/paper/2305.14993/) (2023)
- [Simplicity Level Estimate (SLE): A Learned Reference-Less Metric for Sentence Simplification](https://mlsanity.com/paper/2310.08170/) (2023)
- [Construction Grammar Provides Unique Insight into Neural Language Models](https://mlsanity.com/paper/2302.02178/) (2023)
- [SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pages](https://mlsanity.com/paper/2305.19204/) (2023)
- [A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education](https://mlsanity.com/paper/2501.05220/) (2025)
- [ReadCtrl: Personalizing text generation with readability-controlled instruction learning](https://mlsanity.com/paper/2406.09205/) (2024)
- [How May I Help You? Using Neural Text Simplification to Improve Downstream NLP Tasks](https://mlsanity.com/paper/2109.04604/) (2021)
- [The SAMER Arabic Text Simplification Corpus](https://mlsanity.com/paper/2404.18615/) (2024)
- [Exploring Large Language Models to generate Easy to Read content](https://mlsanity.com/paper/2407.20046/) (2024)
- [Investigating Large Language Models and Control Mechanisms to Improve Text Readability of Biomedical Abstracts](https://mlsanity.com/paper/2309.13202/) (2023)
- [GRS: Combining Generation and Revision in Unsupervised Sentence Simplification](https://mlsanity.com/paper/2203.09742/) (2022)

## Abstract (arXiv)

Text simplification aims at making a text easier to read and understand by simplifying grammar and structure while keeping the underlying information identical. It is often considered an all-purpose generic task where the same simplification is suitable for all; however multiple audiences can benefit from simplified text in different ways. We adapt a discrete parametrization mechanism that provides explicit control on simplification systems based on Sequence-to-Sequence models. As a result, users can condition the simplifications returned by a model on attributes such as length, amount of paraphrasing, lexical complexity and syntactic complexity. We also show that carefully chosen values of these attributes allow out-of-the-box Sequence-to-Sequence models to outperform their standard counterparts on simplification benchmarks. Our model, which we call ACCESS (as shorthand for AudienCe-CEntric Sentence Simplification), establishes the state of the art at 41.87 SARI on the WikiLarge test set, a +1.42 improvement over the best previously reported score.