# Iterative Edit-Based Unsupervised Sentence Simplification

arXiv: https://arxiv.org/abs/2006.09639 · HTML: https://mlsanity.com/paper/2006.09639/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2020.

## Built on by (most cited first, 30 of 33)

- [GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models](https://mlsanity.com/paper/2203.07281/) (2022)
- [LENS: A Learnable Evaluation Metric for Text Simplification](https://mlsanity.com/paper/2212.09739/) (2022)
- [Generating Summaries with Controllable Readability Levels](https://mlsanity.com/paper/2310.10623/) (2023)
- [Improving Iterative Text Revision by Learning Where to Edit from Other Revision Tasks](https://mlsanity.com/paper/2212.01350/) (2022)
- [Text Revision by On-the-Fly Representation Optimization](https://mlsanity.com/paper/2204.07359/) (2022)
- [Prompt-Based Editing for Text Style Transfer](https://mlsanity.com/paper/2301.11997/) (2023)
- [Generating Fluent Fact Checking Explanations with Unsupervised Post-Editing](https://mlsanity.com/paper/2112.06924/) (2021)
- [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)
- [Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization](https://mlsanity.com/paper/2205.14521/) (2022)
- [Machine-in-the-Loop Rewriting for Creative Image Captioning](https://mlsanity.com/paper/2111.04193/) (2021)
- [ReadCtrl: Personalizing text generation with readability-controlled instruction learning](https://mlsanity.com/paper/2406.09205/) (2024)
- [What Goes Into a LM Acceptability Judgment? Rethinking the Impact of Frequency and Length](https://mlsanity.com/paper/2411.02528/) (2024)
- [Search and Learn: Improving Semantic Coverage for Data-to-Text Generation](https://mlsanity.com/paper/2112.02770/) (2021)
- [GRS: Combining Generation and Revision in Unsupervised Sentence Simplification](https://mlsanity.com/paper/2203.09742/) (2022)
- [Simulated annealing for optimization of graphs and sequences](https://mlsanity.com/paper/2110.01384/) (2021)
- [Improving Zero-Shot Event Extraction via Sentence Simplification](https://mlsanity.com/paper/2204.02531/) (2022)
- [Exploiting Summarization Data to Help Text Simplification](https://mlsanity.com/paper/2302.07124/) (2023)
- [StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2212.09670/) (2022)
- [A New Dataset and Empirical Study for Sentence Simplification in Chinese](https://mlsanity.com/paper/2306.04188/) (2023)
- [Simulated Annealing for Emotional Dialogue Systems](https://mlsanity.com/paper/2109.10715/) (2021)
- [Context-Aware Document Simplification](https://mlsanity.com/paper/2305.06274/) (2023)
- [Aligning Sentence Simplification with ESL Learner's Proficiency for Language Acquisition](https://mlsanity.com/paper/2502.11457/) (2025)
- [Unsupervised Sentence Simplification via Dependency Parsing](https://mlsanity.com/paper/2206.12261/) (2022)
- [Search and Learning for Unsupervised Text Generation](https://mlsanity.com/paper/2309.09497/) (2023)
- [BoschAI @ PLABA 2023: Leveraging Edit Operations in End-to-End Neural Sentence Simplification](https://mlsanity.com/paper/2311.01907/) (2023)
- [Edit-Constrained Decoding for Sentence Simplification](https://mlsanity.com/paper/2409.19247/) (2024)
- [Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model](https://mlsanity.com/paper/2502.01090/) (2025)
- [An Empirical Study on Learning and Improving the Search Objective for Unsupervised Paraphrasing](https://mlsanity.com/paper/2203.12106/) (2022)

## Abstract (arXiv)

We present a novel iterative, edit-based approach to unsupervised sentence simplification. Our model is guided by a scoring function involving fluency, simplicity, and meaning preservation. Then, we iteratively perform word and phrase-level edits on the complex sentence. Compared with previous approaches, our model does not require a parallel training set, but is more controllable and interpretable. Experiments on Newsela and WikiLarge datasets show that our approach is nearly as effective as state-of-the-art supervised approaches.