mlsanityData to 7 Oct 2026

An Open Multilingual System for Scoring Readability of Wikipedia

arXiv 2406.01835 ↗First posted 3 Jun 2024cs.CL cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

With over 60M articles, Wikipedia has become the largest platform for open and freely accessible knowledge. While it has more than 15B monthly visits, its content is believed to be inaccessible to many readers due to the lack of readability of its text. However, previous investigations of the readability of Wikipedia have been restricted to English only, and there are currently no systems supporting the automatic readability assessment of the 300+ languages in Wikipedia. To bridge this gap, we develop a multilingual model to score the readability of Wikipedia articles. To train and evaluate this model, we create a novel multilingual dataset spanning 14 languages, by matching articles from Wikipedia to simplified Wikipedia and online children encyclopedias. We show that our model performs well in a zero-shot scenario, yielding a ranking accuracy of more than 80% across 14 languages and improving upon previous benchmarks. These results demonstrate the applicability of the model at scale for languages in which there is no ground-truth data available for model fine-tuning. Furthermore, we provide the first overview on the state of readability in Wikipedia beyond English.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 26 of its 86 references that are in the map. First posted on arXiv 3 Jun 2024.

Builds on

26 of 86 references.

References · 26

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,346
  3. 2019How multilingual is Multilingual BERT?cited by 642
  4. 2021Quality at a Glance: An Audit of Web-Crawled Multilingual Datasetscited by 241
  5. 2020Are All Languages Created Equal in Multilingual BERT?cited by 206
  6. 2017Sentence Simplification with Deep Reinforcement Learningcited by 107
  7. 2020Neural CRF Model for Sentence Alignment in Text Simplificationcited by 106
  8. 2019Text Readability Assessment for Second Language Learnerscited by 54
  9. 2019Supervised and Unsupervised Neural Approaches to Text Readabilitycited by 45
  10. 2020Linguistic Features for Readability Assessmentcited by 35
  11. 2021Trends, Limitations and Open Challenges in Automatic Readability Assessment Researchcited by 28
  12. 2017CatBoost: unbiased boosting with categorical featurescited by 27
14 more
  1. 2021Document-Level Text Simplification: Dataset, Criteria and Baselinecited by 27
  2. 2021BERT Embeddings for Automatic Readability Assessmentcited by 19
  3. 2018Why the World Reads Wikipedia: Beyond English Speakerscited by 15
  4. 2022A Neural Pairwise Ranking Model for Readability Assessmentcited by 14
  5. 2023SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pagescited by 12
  6. 2022A Baseline Readability Model for Cebuanocited by 10
  7. 2023mLongT5: A Multilingual and Efficient Text-To-Text Transformer for Longer Sequencescited by 10
  8. 2023Automatic Readability Assessment for Closely Related Languagescited by 9
  9. 2023Prompt-based Learning for Text Readability Assessmentcited by 8
  10. 2019Text as Environment: A Deep Reinforcement Learning Text Readability Assessment Modelcited by 7
  11. 2022Automatic Readability Assessment of German Sentences with Transformer Ensemblescited by 7
  12. 2017Why We Read Wikipediacited by 6
  13. 2020Global gender differences in Wikipedia readershipcited by 4
  14. 2020WikiHist.html: English Wikipedia's Full Revision History in HTML Formatcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 2.

7 papers.

  1. 2025MO-GRPO: Mitigating Reward Hacking of Group Relative Policy Optimization on Multi-Objective Problemscited by 21
  2. 2025Wikipedia in the Era of LLMs: Evolution and Riskscited by 4
  3. 2025MULTITAT: Benchmarking Multilingual Table-and-Text Question Answeringcited by 2
  4. 2026Multilingual Reference Need Assessment System for Wikipediacited by 1
  5. 2025Gatsby Without the 'E': Crafting Lipograms with LLMscited by 0
  6. 2025Hidden Persuasion: Detecting Manipulative Narratives on Social Media During the 2022 Russian Invasion of Ukrainecited by 0
  7. 2026An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generationcited by 0