mlsanityData to 7 Oct 2026

Controllable Sentence Simplification

arXiv 1910.02677 ↗First posted 7 Oct 2019cs.CLcited by 78

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 14; 2023: 29; 2024: 14; 2025: 9; 2026: 7.

78 papers.

Sort:

By area:

  1. 2022LENS: A Learnable Evaluation Metric for Text Simplificationcited by 54
  2. 2021Keep it Simple: Unsupervised Simplification of Multi-Paragraph Textcited by 45
  3. 2022Evaluating Factuality in Text Simplificationcited by 34
  4. 2023BLESS: Benchmarking Large Language Models on Sentence Simplificationcited by 34
  5. 2024Towards Optimizing the Costs of LLM Usagecited by 33
  6. 2023Training Models to Generate, Recognize, and Reframe Unhelpful Thoughtscited by 31
  7. 2021Text Simplification by Taggingcited by 27
  8. 2023Revisiting non-English Text Simplification: A Unified Multilingual Benchmarkcited by 27
  9. 2023Generating Summaries with Controllable Readability Levelscited by 24
  10. 2024Natural Language Processing in the Patent Domain: A Surveycited by 20
  11. 2022Towards Process-Oriented, Modular, and Versatile Question Generation that Meets Educational Needscited by 19
  12. 2022Why is constrained neural language generation particularly challenging?cited by 19
38 more
  1. 2022Multitasking Framework for Unsupervised Simple Definition Generationcited by 18
  2. 2021Rethinking Automatic Evaluation in Sentence Simplificationcited by 17
  3. 2023Med-EASi: Finely Annotated Dataset and Models for Controllable Simplification of Medical Textscited by 16
  4. 2023Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading Comprehensioncited by 16
  5. 2023Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSAcited by 15
  6. 2021An Unsupervised Method for Building Sentence Simplification Corpora in Multiple Languagescited by 14
  7. 2023Sentence Simplification via Large Language Modelscited by 14
  8. 2023Controlling Pre-trained Language Models for Grade-Specific Text Simplificationcited by 14
  9. 2023Simplicity Level Estimate (SLE): A Learned Reference-Less Metric for Sentence Simplificationcited by 14
  10. 2023Construction Grammar Provides Unique Insight into Neural Language Modelscited by 13
  11. 2023SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pagescited by 12
  12. 2025A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Educationcited by 11
  13. 2024ReadCtrl: Personalizing text generation with readability-controlled instruction learningcited by 10
  14. 2021How May I Help You? Using Neural Text Simplification to Improve Downstream NLP Taskscited by 9
  15. 2024The SAMER Arabic Text Simplification Corpuscited by 9
  16. 2024Exploring Large Language Models to generate Easy to Read contentcited by 9
  17. 2023Investigating Large Language Models and Control Mechanisms to Improve Text Readability of Biomedical Abstractscited by 8
  18. 2022GRS: Combining Generation and Revision in Unsupervised Sentence Simplificationcited by 6
  19. 2025Opportunities and Challenges of LLMs in Education: An NLP Perspectivecited by 6
  20. 2023Exploiting Summarization Data to Help Text Simplificationcited by 5
  21. 2023Reducing Sequence Length by Predicting Edit Operations with Large Language Modelscited by 5
  22. 2024Evaluating Document Simplification: On the Importance of Separately Assessing Simplicity and Meaning Preservationcited by 5
  23. 2022(Psycho-)Linguistic Features Meet Transformer Models for Improved Explainable and Controllable Text Simplificationcited by 4
  24. 2023A New Dataset and Empirical Study for Sentence Simplification in Chinesecited by 4
  25. 2023Automatic and Human-AI Interactive Text Generationcited by 4
  26. 2024An In-depth Evaluation of Large Language Models in Sentence Simplification with Error-based Human Assessmentcited by 4
  27. 2022Unsupervised Simplification of Legal Textscited by 3
  28. 2023SimpLex: a lexical text simplification architecturecited by 3
  29. 2023Text Simplification of Scientific Texts for Non-Expert Readerscited by 3
  30. 2023Creating a silver standard for patent simplificationcited by 3
  31. 2024Can Large Language Models (or Humans) Disentangle Text?cited by 3
  32. 2024Label Confidence Weighted Learning for Target-level Sentence Simplificationcited by 3
  33. 2024SiTSE: Sinhala Text Simplification Dataset and Evaluationcited by 3
  34. 2025Aligning Sentence Simplification with ESL Learner's Proficiency for Language Acquisitioncited by 3
  35. 2022Unsupervised Sentence Simplification via Dependency Parsingcited by 2
  36. 2022Cognitive Simplification Operations Improve Text Simplificationcited by 2
  37. 2022Explain to me like I am five -- Sentence Simplification Using Transformerscited by 2
  38. 2023Mitigating Data Scarcity for Large Language Modelscited by 2

50 most cited of 78 All 78 (JSON)