---
title: "BAREC Demo — paper by Altarbouch et al. (2025)"
description: "This demo paper presents a public web system built on the BAREC corpus, which rates individual… 26 references, cited by 1 paper here."
authors: ["Kinda Altarbouch", "Khalid N. Elmadani", "Ossama Obeid", "Hanada Taha", "Nizar Habash"]
year: 2025
venue: "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations"
source: "https://aclanthology.org/2025.emnlp-demos.74/"
doi: "10.18653/v1/2025.emnlp-demos.74"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/altarbouch-2025-barec-demo-resources-tools-sentence/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/altarbouch-2025-barec-demo-resources-tools-sentence/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/15/) / BAREC Demo: Resources and Tools for Sentence-level Arabic Readability Assessment

# BAREC Demo: Resources and Tools for Sentence-level Arabic Readability Assessment

**Authors:** Kinda Altarbouch, [Khalid N. Elmadani](https://md.research.elamur.ai/free/en/authors/khalid-n-elmadani/), [Ossama Obeid](https://md.research.elamur.ai/free/en/authors/ossama-obeid/), [Hanada Taha](https://md.research.elamur.ai/free/en/authors/hanada-taha/) and [Nizar Habash](https://md.research.elamur.ai/free/en/authors/nizar-habash/) · **Year:** 2025 · **Venue:** [Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations](https://md.research.elamur.ai/free/en/venues/emnlp/) ([EMNLP 2025](https://md.research.elamur.ai/free/en/venues/emnlp/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.emnlp-demos.74/) · [PDF](https://aclanthology.org/2025.emnlp-demos.74.pdf) · [DOI 10.18653/v1/2025.emnlp-demos.74](https://doi.org/10.18653/v1/2025.emnlp-demos.74) · [OpenAlex](https://openalex.org/W4416037532)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/altarbouch-2025-barec-demo-resources-tools-sentence/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Picking Arabic texts that fit a learner's level is difficult. The language has rich morphology, optional diacritics and flexible word order, and its standard and dialectal varieties coexist. Earlier Arabic readability work mostly scored whole documents or single words and covered few genres. This demo paper presents a public web system built on the BAREC corpus, which rates individual sentences on a 19-level scale from kindergarten to postgraduate. The scale is derived from the Taha/Arabi21 leveling framework.

The system has two parts:
- **Search** lets users browse the manually labelled corpus by book, author or words, with Arabic-aware matching.
- **Analyze** labels every sentence of pasted text using a fine-tuned AraBERTv02 classifier. It also assigns an overall text level, defined as the highest level among the sentences.

On the BAREC test set the classifier reaches 55.8% exact accuracy at 19 levels and a QWK of 81.0%. Its errors are usually close to the gold level.

The tool gives Arabic teachers and content creators fine-grained difficulty feedback. It also gives researchers an open resource that could support evaluation of text simplification.

## Key points
- The BAREC corpus has about 69K sentences (1M words) from 1,922 documents and 30 sources. Roughly a quarter of the sentences were transcribed by hand from sources not previously digitized. Documents are tagged with three domains (Arts & Humanities, Social Sciences, STEM) and three readership groups (Foundational, Advanced, Specialized).
- The 19 levels are arranged in a "pyramid" that can be collapsed into coarser 7-, 5- and 3-level schemes.
- The model is AraBERTv02 fine-tuned with cross-entropy loss (the AraBERTv02+Word+CE setup). Training ran for 6 epochs on a V100 with learning rate 5e-5 and batch size 64.
- Test results:

  | Metric | Score |
  |---|---|
  | Acc, 19 levels | 55.8% |
  | Acc, 7 levels | 64.9% |
  | Acc, 5 levels | 69.1% |
  | Acc, 3 levels | 74.7% |
  | ±1 accuracy (19 levels) | 69.4% |
  | Mean distance from gold | 1.09 |
  | QWK | 81.0% |

- The stack is PostgreSQL full-text search, Express.js, EJS templates and REST APIs, with an Arabic/English interface. Code is MIT-licensed and data is CC-BY-SA-4.0.

## Interesting ideas
- The fine label scale is built so it can be merged into coarser nested scales, and one model is scored at every granularity, which shows how much error is "near miss" versus truly wrong.
- Ordered labels are evaluated with more than exact match: within-one accuracy, mean absolute distance and quadratic weighted kappa all reward predictions that land close to the gold level.
- A passage's difficulty is the maximum of its sentence scores, so the result names the specific sentences that make the text hard rather than hiding them in an average.
- The same orthographic normalization is applied to both the stored index and the incoming query, plus partial matching to catch affixed forms, so spelling variation never blocks a match.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (learn): Score tagger or role predictions at both fine and merged label sets (e.g. full UD relations vs. coarse classes) to tell boundary confusions from gross errors.
- **I2** (answer): When grading Mova's answers on graded school-course tests, report distance-aware scores so that a slightly-off level or quantity counts differently from a wild miss.
- **I3** (answer): Rate fables per sentence and report the hardest sentence, explaining where the reader is likely to fail.
- **I4** (tokens): Run one shared normalization function on lexicon entries and on input tokens (quotes, hyphenation, spelling variants) so lookups stay consistent and explainable.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [New York University Abu Dhabi](https://md.research.elamur.ai/free/en/universities/new-york-university-abu-dhabi/) — University, Abu Dhabi, United Arab Emirates · 124 works · 4,709 citations
- [Zayed University](https://md.research.elamur.ai/free/en/universities/zayed-university/) — University, Abu Dhabi, United Arab Emirates · 6 works · 67 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,954 works · [🎓 Education](https://md.research.elamur.ai/free/en/shelves/social-sciences/education/) · 212 works

🧭 Topics (1): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 3,066 works

## Cite

Cite as: Kinda Altarbouch, Khalid N. Elmadani, Ossama Obeid, Hanada Taha and Nizar Habash. 2025. BAREC Demo: Resources and Tools for Sentence-level Arabic Readability Assessment. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{altarbouch2025barec,
  title = {{BAREC Demo: Resources and Tools for Sentence-level Arabic Readability Assessment}},
  author = {Kinda Altarbouch, Khalid N. Elmadani, Ossama Obeid, Hanada Taha and Nizar Habash},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations},
  year = {2025},
  doi = {10.18653/v1/2025.emnlp-demos.74},
  url = {https://doi.org/10.18653/v1/2025.emnlp-demos.74}
}
```

- [← previous Baoflowin502 at MAHED Shared Task: Text-based Hate and Hope Speech Classification](https://md.research.elamur.ai/free/en/papers/bao-2025-baoflowin502-mahed-shared-task-text/)
- [next → Batch-wise Convergent Pre-training: Step-by-Step Learning Inspired by Child Language Development](https://md.research.elamur.ai/free/en/papers/yoshida-2025-batch-wise-convergent-pre-training/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/15/)

## References

26 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Muhamed Al Khalil, Nizar Habash, and Hind Saddiki. 2017. Simplification of Arabic masterpieces for extensive reading: A project overview. Procedia Computer Science, 117:192–198. [find](https://scholar.google.com/scholar?q=Muhamed+Al+Khalil%2C+Nizar+Habash%2C+and+Hind+Saddiki%2E+2017%2E+Simplification+of+Arabic+masterpieces+for+extensive+reading%3A+A+project+overview%2E+Procedia+Computer+Science%2C+117%3A192%E2%80%93198%2E)
2. Muhamed Al Khalil, Hind Saddiki, Nizar Habash, and Latifa Alfalasi. 2018. [A Leveled Reading Corpus of Modern Standard Arabic](https://md.research.elamur.ai/free/en/papers/khalil-2018-leveled-reading-corpus-modern-standard/). In Proceedings of the Language Resources and Evaluation Conference (LREC), Miyazaki, Japan.
3. Abdel Karim Al Tamimi, Manar Jaradat, Nuha Al-Jarrah, and Sahar Ghanem. 2014. AARI: automatic Arabic readability index. International Arab Journal of Information Technology, 11(4):370–378. [find](https://scholar.google.com/scholar?q=Abdel+Karim+Al+Tamimi%2C+Manar+Jaradat%2C+Nuha+Al%2DJarrah%2C+and+Sahar+Ghanem%2E+2014%2E+AARI%3A+automatic+Arabic+readability+index%2E+International+Arab+Journal+of+Information+Technology%2C+11%284%29%3A370%E2%80%93378%2E)
4. Bashar Alhafni, Reem Hazim, Juan David Pineros Liberato, Muhamed Al Khalil, and Nizar Habash. 2024. [The SAMER Arabic text simplification corpus](https://md.research.elamur.ai/free/en/papers/alhafni-2024-samer-arabic-text-simplification-corpus/). In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 16079–16093, Torino, Italia. ELRA and ICCL.
5. Wissam Antoun, Fady Baly, and Hazem Hajj. 2020. [AraBERT: Transformer-based model for Arabic language understanding](https://md.research.elamur.ai/free/en/papers/antoun-2020-arabert-transformer-based-model-arabic/). In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pages 9–15, Marseille, France. European Language Resource Association. [↗](https://doi.org/10.48550/arxiv.2003.00104)
6. Jacob Cohen. 1968. Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit. Psychological bulletin, 70(4):213. [↗](https://doi.org/10.1037/h0026256)
7. Afrizal Doewes, Nughthoh Arfawi Kurdhi, and Akrati Saxena. 2023. Evaluating quadratic weighted kappa as the standard performance metric for automated essay scoring. In Proceedings of the 16th International Conference on Educational Data Mining, pages 103– 113, Bengaluru, India. International Educational Data Mining Society. [find](https://scholar.google.com/scholar?q=Afrizal+Doewes%2C+Nughthoh+Arfawi+Kurdhi%2C+and+Akrati+Saxena%2E+2023%2E+Evaluating+quadratic+weighted+kappa+as+the+standard+performance+metric+for+automated+essay+scoring%2E+In+Proceedings+of+the+16th+Internat)
8. William H DuBay. 2004. The principles of readability. Online Submission. [find](https://scholar.google.com/scholar?q=William+H+DuBay%2E+2004%2E+The+principles+of+readability%2E+Online+Submission%2E)
9. Mahmoud El-Haj and Paul Rayson. 2016. OSMAN: A novel Arabic readability metric. In Proceedings of the Language Resources and Evaluation Conference (LREC), Portorož, Slovenia. [find](https://scholar.google.com/scholar?q=Mahmoud+El%2DHaj+and+Paul+Rayson%2E+2016%2E+OSMAN%3A+A+novel+Arabic+readability+metric%2E+In+Proceedings+of+the+Language+Resources+and+Evaluation+Conference+%28LREC%29%2C+Portoro%C5%BE%2C+Slovenia%2E)
10. Khalid N. Elmadani, Nizar Habash, and Hanada Taha-Thomure. 2025. [A large and balanced corpus for fine-grained Arabic readability assessment](https://md.research.elamur.ai/free/en/papers/elmadani-2025-large-balanced-corpus-fine-grained/). In Findings of the Association for Computational Linguistics: ACL 2025, Vienna, Austria. Association for Computational Linguistics.
11. Charles F Ferguson. 1959. Diglossia. Word, 15(2):325– 340. [find](https://scholar.google.com/scholar?q=Charles+F+Ferguson%2E+1959%2E+Diglossia%2E+Word%2C+15%282%29%3A325%E2%80%93+340%2E)
12. Jonathan Forsyth. 2014. Automatic readability prediction for modern standard Arabic. In Proceedings of the Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT). [find](https://scholar.google.com/scholar?q=Jonathan+Forsyth%2E+2014%2E+Automatic+readability+prediction+for+modern+standard+Arabic%2E+In+Proceedings+of+the+Workshop+on+Open%2DSource+Arabic+Corpora+and+Processing+Tools+%28OSACT%29%2E)
13. Nizar Habash and David Palfreyman. 2022. ZAEBUC: An annotated Arabic-English bilingual writer corpus. In Proceedings of the Language Resources and Evaluation Conference (LREC), Marseille, France. [find](https://scholar.google.com/scholar?q=Nizar+Habash+and+David+Palfreyman%2E+2022%2E+ZAEBUC%3A+An+annotated+Arabic%2DEnglish+bilingual+writer+corpus%2E+In+Proceedings+of+the+Language+Resources+and+Evaluation+Conference+%28LREC%29%2C+Marseille%2C+France%2E)
14. Nizar Habash, Abdelhadi Soudi, and Tim Buckwalter. 2007. On Arabic Transliteration. In A. van den Bosch and A. Soudi, editors, Arabic Computational Morphology: Knowledge-based and Empirical Methods, pages 15–22. Springer, Netherlands. [↗](https://doi.org/10.1007/978-1-4020-6046-5_2)
15. Nizar Habash, Hanada Taha-Thomure, Khalid N. Elmadani, Zeina Zeino, and Abdallah Abushmaes. 2025. [Guidelines for fine-grained sentence-level Arabic readability annotation](https://md.research.elamur.ai/free/en/papers/habash-2025-guidelines-fine-grained-sentence-level/). In Proceedings of the 19th Linguistic Annotation Workshop (LAW-XIX-2025), Vienna, Austria. Association for Computational Linguistics.
16. Nizar Y Habash. 2010. Introduction to Arabic natural language processing, volume 3. Morgan & Claypool Publishers. [find](https://scholar.google.com/scholar?q=Nizar+Y+Habash%2E+2010%2E+Introduction+to+Arabic+natural+language+processing%2C+volume+3%2E+Morgan+%26+Claypool+Publishers%2E)
17. Reem Hazim, Hind Saddiki, Bashar Alhafni, Muhamed Al Khalil, and Nizar Habash. 2022. [Arabic word-level readability visualization for assisted text simplification](https://md.research.elamur.ai/free/en/papers/hazim-2022-arabic-word-level-readability-visualization/). In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 242–249, Abu Dhabi, UAE. Association for Computational Linguistics.
18. Zhengyang Jiang, Nizar Habash, and Muhamed Al Khalil. 2020. [An online readability leveled Arabic thesaurus](https://md.research.elamur.ai/free/en/papers/jiang-2020-online-readability-leveled-arabic-thesaurus/). In Proceedings of the 28th International Conference on Computational Linguistics: System Demonstrations, pages 59–63, Barcelona, Spain (Online). International Committee on Computational Linguistics (ICCL).
19. Adam Kilgarriff, Frieda Charalabopoulou, Maria Gavrilidou, Janne Bondi Johannessen, Saussan Khalil, Sofie Johansson Kokkinakis, Robert Lew, Serge Sharoff, Ravikiran Vadlapudi, and Elena Volodina. 2014. Corpus-based vocabulary lists for language learners for nine languages. Language Resources and Evaluation, 48(1):121–163. [↗](https://doi.org/10.1007/s10579-013-9251-2)
20. Juan Liberato, Bashar Alhafni, Muhamed Khalil, and Nizar Habash. 2024. [Strategies for Arabic readability modeling](https://md.research.elamur.ai/free/en/papers/liberato-2024-strategies-arabic-readability-modeling/). In Proceedings of The Second Arabic Natural Language Processing Conference, pages 55– 66, Bangkok, Thailand.
21. Tarek Naous, Michael J. Ryan, Anton Lavrouk, Mohit Chandra, and Wei Xu. 2023. Readme++: Benchmarking multilingual language models for multi-domain readability assessment. Preprint, arXiv:2305.14463. [↗](https://arxiv.org/abs/2305.14463)
22. Nobal Niraula, Vasile Rus, Rajendra Banjade, Dan Stefanescu, William Baggett, and Brent Morgan. 2014. The DARE corpus: A resource for anaphora resolution in dialogue based intelligent tutoring systems. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), pages 3199–3203, Reykjavik, Iceland. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Nobal+Niraula%2C+Vasile+Rus%2C+Rajendra+Banjade%2C+Dan+Stefanescu%2C+William+Baggett%2C+and+Brent+Morgan%2E+2014%2E+The+DARE+corpus%3A+A+resource+for+anaphora+resolution+in+dialogue+based+intelligent+tutoring+systems)
23. Ossama Obeid, Nasser Zalmout, Salam Khalifa, Dima Taji, Mai Oudah, Bashar Alhafni, Go Inoue, Fadhl Eryani, Alexander Erdmann, and Nizar Habash. 2020. [CAMeL tools: An open source python toolkit for Arabic natural language processing](https://md.research.elamur.ai/free/en/papers/obeid-2020-camel-tools-open-source-python/). In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 7022–7032, Marseille, France.
24. Hind Saddiki, Nizar Habash, Violetta Cavalli-Sforza, and Muhamed Al Khalil. 2018. [Feature optimization for predicting readability of arabic l1 and l2](https://md.research.elamur.ai/free/en/papers/saddiki-2018-feature-optimization-predicting-readability-arabic/). In Proceedings of the 5th Workshop on Natural Language Processing Techniques for Educational Applications, pages 20–29. [↗](https://doi.org/10.60692/v8hb7-91m29)
25. Rasha Soliman and Laila Familiar. 2024. Creating a cefr arabic vocabulary profile: A frequency-based multi-dialectal approach. Critical Multilingualism Studies, 11(1):266–286. [↗](https://doi.org/10.2458/cms.6483)
26. Hanada Taha-Thomure. 2017. Arabic Language Text  ñJ‚Ó J ’JË é£ @XA Jë Q K AªÓ Leveling ( ñ’ JË@ HAK éJ  K. QªË@ ). Educational   ( ©K Pñ JË@ð Qå„ JÊË ø ñK. Q Ë@ H. AJºË@ P@X ) . Book House Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R’emi Louf, Morgan Funtowicz, and Jamie Brew. 2019. Huggingface’s [transformers: State-of-the-art natural language processing](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/). ArXiv, abs/1910.03771. *Figure 5: BAREC Demo search interface. The main search UI allows querying by sentence, author, or book. Users can navigate annotated dataset entries and expand metadata by clicking the (+) icon. The query Q ‚ ®K tfsyr ‘explanation’ returns morphologically related forms.* *Figure 6: The BAREC Demo Analyze Interface, including the text input area, the Readability Bar (colored guide bar for readability level), the overall Text Readability Level, and the detailed, sentence-by-sentence readability levels.* [↗](https://arxiv.org/abs/1910.03771)

*Updated 1 November 2026*