---
title: "MorphoArabia at BAREC Shared Task 2025: A Hybrid"
description: "The paper describes MorphoArabia, a system entered in the BAREC Shared Task 2025. 15 references, cited by 1 paper here."
authors: ["Mohamed Emad Elden, Fatimah"]
year: 2025
venue: "Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks"
source: "https://aclanthology.org/2025.arabicnlp-sharedtasks.41/"
doi: "10.18653/v1/2025.arabicnlp-sharedtasks.41"
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/elden-2025-morphoarabia-barec-shared-task-2025/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/elden-2025-morphoarabia-barec-shared-task-2025/)

[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/) / MorphoArabia at BAREC Shared Task 2025: A Hybrid Architecture with Morphological Analysis for Arabic Readability Assessment

# MorphoArabia at BAREC Shared Task 2025: A Hybrid Architecture with Morphological Analysis for Arabic Readability Assessment

**Authors:** [Mohamed Emad Elden, Fatimah](https://md.research.elamur.ai/free/en/authors/mohamed-emad-elden-fatimah/) · **Year:** 2025 · **Venue:** [Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks](https://md.research.elamur.ai/free/en/venues/arabicnlp/) ([ArabicNLP 2025](https://md.research.elamur.ai/free/en/venues/arabicnlp/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.arabicnlp-sharedtasks.41/) · [PDF](https://aclanthology.org/2025.arabicnlp-sharedtasks.41.pdf) · [DOI 10.18653/v1/2025.arabicnlp-sharedtasks.41](https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.41) · [OpenAlex](https://openalex.org/W4416037812)

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

## Summary
The paper describes MorphoArabia, a system entered in the BAREC Shared Task 2025. The task asks systems to assign Arabic sentences and documents to one of 19 readability levels. The authors argue that Arabic difficulty depends heavily on morphology. Their pipeline therefore segments text into morphemes with the CAMeL Tools d3tok analyzer and then fine-tunes AraBERTv2 as a regressor that predicts a continuous level.

The system was adapted to each track:
- **Strict:** BAREC data only.
- **Constrained:** BAREC plus SAMER, with seven lexicon-based features appended to the [CLS] vector.
- **Open:** BAREC plus DARES.

Document scores are not modelled directly. Each document receives the highest score predicted for any of its sentences.

The system placed in the top 10 in all six subtasks. Its best sentence-level result was 84.2% QWK on the Strict track, and it took 2nd place on the Strict and Open document tasks. Adding external corpora did not beat the BAREC-only model. The authors attribute this to noise from mapping incompatible label scales onto one scheme. The work shows that a morphology-first pipeline is a strong and reproducible baseline.

## Key points
- **Data:** BAREC has over 1M words on a 19-level scale. Strict training used 54,845 sentences. The Constrained training set grew to 97,874 sentences after adding SAMER.
- **Blind-test QWK (sentence / document):**
  - Strict: 84.2 / 79.9
  - Constrained: 82.9 / 75.5
  - Open: 83.9 / 79.2
  - Official baseline: 81.5 / 62.0
- **Rankings:**
  - Sentence level: 7th (Strict), 3rd (Constrained), 2nd (Open).
  - Document level: 2nd (Strict), 3rd (Constrained), 2nd (Open).
- **Label mapping:** SAMER levels L3/L4/L5 were mapped heuristically to BAREC 4/10/16. DARES grades G1–G12 were mapped to BAREC 1–12. Combining all three corpora did not help.
- **Ablation and errors:**
  - Regression beat 19-way classification. However, the classification runs also used a non-morphological normalization pipeline, so the two factors are not cleanly separated.
  - A known error source is d3tok emitting NOAN for unknown or rare word forms.

## Interesting ideas
- Scoring a document by its hardest sentence instead of averaging fits cases where a few difficult outliers decide overall difficulty; it is also trivially explainable.
- Ordinal labels are treated as a continuous regression target and evaluated with QWK, which penalizes distant mistakes more than near misses.
- The analyzer's failure marker (NOAN) is visible in the output, so failures can be counted and traced as a concrete error source.
- Merging corpora whose annotation scales were heuristically aligned made results worse, showing that label consistency can matter more than data volume.
- The best model at sentence level was not the best at document level, so model selection should use the aggregate metric that is actually needed.

## For Mova

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

- **I1** (answer): a reader could rate a school text's difficulty by pointing to the single sentence that drives the rating.
- **I2** (learn): ordinal outputs such as difficulty or confidence grades could be scored with a quadratic-weighted metric rather than plain accuracy.
- **I3** (tokens): the morphology layer should emit an explicit "no analysis" flag and track its rate, since one unanalyzed word can distort downstream decisions.
- **I4** (tree): before pooling treebanks converted between UD dialects, check whether the converted labels agree, and keep a single-source model as a control.
- **I5** (learn): choose parser or frame checkpoints by the final-answer metric, not only by per-token scores.

*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

- [Cairo University](https://md.research.elamur.ai/free/en/universities/cairo-university/) — University, Giza, Egypt · 42 works · 1,350 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (2): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works · [🧩 Morphology](https://md.research.elamur.ai/free/en/topics/morphology/) · 405 works

## Cite

Cite as: Mohamed Emad Elden, Fatimah. 2025. MorphoArabia at BAREC Shared Task 2025: A Hybrid Architecture with Morphological Analysis for Arabic Readability Assessment. Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks.

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

```bibtex
@inproceedings{fatimah2025morphoarabia,
  title = {{MorphoArabia at BAREC Shared Task 2025: A Hybrid Architecture with Morphological Analysis for Arabic Readability Assessment}},
  author = {Mohamed Emad Elden, Fatimah},
  booktitle = {Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks},
  year = {2025},
  doi = {10.18653/v1/2025.arabicnlp-sharedtasks.41},
  url = {https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.41}
}
```

- [← previous MLInitiative at CASE 2025: Multimodal Detection of Hate Speech, Humor,and Stance using Transformers](https://md.research.elamur.ai/free/en/papers/acharya-2025-mlinitiative-case-2025-multimodal-detection/)
- [next → mucAI at AraHealthQA 2025: Explain–Retrieve–Verify (ERV) Workflow for Multi-Label Arabic Health QA Classification](https://md.research.elamur.ai/free/en/papers/abdou-2025-mucai-arahealthqa-2025-explain-retrieve/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/15/)

## References

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

1. Abeer AL-Dayel, Hend Al-Khalifa, Sinaa Alaqeel, Norah Abanmy, Maha Al-Yahya, and Mona Diab. 2018. ARC-WMI: Towards building Arabic readability corpus for written medicine information. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Abeer+AL%2DDayel%2C+Hend+Al%2DKhalifa%2C+Sinaa+Alaqeel%2C+Norah+Abanmy%2C+Maha+Al%2DYahya%2C+and+Mona+Diab%2E+2018%2E+ARC%2DWMI%3A+Towards+building+Arabic+readability+corpus+for+written+medicine+information%2E+In+Proceedings+o)
2. Abdel-Karim Al-Tamimi, Manar Jaradat, Nuha Aljarrah, and Sahar Ghanim. 2014. AARI: Automatic Arabic Readability Index. The International Arab Journal of Information Technology, 11(4):384–391. [find](https://scholar.google.com/scholar?q=Abdel%2DKarim+Al%2DTamimi%2C+Manar+Jaradat%2C+Nuha+Aljarrah%2C+and+Sahar+Ghanim%2E+2014%2E+AARI%3A+Automatic+Arabic+Readability+Index%2E+The+International+Arab+Journal+of+Information+Technology%2C+11%284%29%3A384%E2%80%93391%2E)
3. 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.
4. Yousef Altaher, Ali Fadel, Mazen Alotaibi, Mazen Alyazidi, Mishari Al-Mutairi, Mutlaq Aldhbuiub, Abdulrahman Mosaibah, Abdelrahman Rezk, Abdulrazzaq Alhendi, Mazen Abo Shal, Emad A. Alghamdi, Maged S. Alshaibani, Jezia Zakraoui, Wafaa Mohammed, Kamel Gaanoun, Khalid N. Elmadani, Mustafa Ghaleb, Nouamane Tazi, Raed Alharbi, and 2 others. 2022. [Masader plus: A new interface for exploring +500 arabic nlp datasets](https://md.research.elamur.ai/free/en/papers/altaher-2022-masader-plus-new-interface-exploring/). Preprint, arXiv:2208.00932. [↗](https://arxiv.org/abs/2208.00932)
5. Zaid Alyafeai, Maraim Masoud, Mustafa Ghaleb, and Maged S. Al-shaibani. 2021. [Masader: Metadata sourcing for arabic text and speech data resources](https://md.research.elamur.ai/free/en/papers/alyafeai-2022-masader-metadata-sourcing-arabic-text/). Preprint, arXiv:2110.06744. [↗](https://arxiv.org/abs/2110.06744)
6. 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)
7. Jacob Cohen. 1968. Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit. Psychological Bulletin, 70(4):213–220. [↗](https://doi.org/10.1037/h0026256)
8. Mahmoud El-Haj and Paul Rayson. 2016. OSMAN — a novel Arabic readability metric. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 250–255, Portorož, Slovenia. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Mahmoud+El%2DHaj+and+Paul+Rayson%2E+2016%2E+OSMAN+%E2%80%94+a+novel+Arabic+readability+metric%2E+In+Proceedings+of+the+Tenth+International+Conference+on+Language+Resources+and+Evaluation+%28LREC%E2%80%9916%29%2C+pages+250%E2%80%93255%2C+Por)
9. Mo El-Haj, Sultan Almujaiwel, Damith Premasiri, Tharindu Ranasinghe, and Ruslan Mitkov. 2024. [DARES: Dataset for Arabic readability estimation of school materials](https://md.research.elamur.ai/free/en/papers/haj-2024-dares-dataset-arabic-readability-estimation/). In Proceedings of the Workshop on DeTermIt! Evaluating Text Difficulty in a Multilingual Context @ LREC-COLING 2024, pages 103– 113, Torino, Italia. ELRA and ICCL.
10. Khalid N. Elmadani, Bashar Alhafni, Hanada Taha, and Nizar Habash. 2025a. [BAREC shared task 2025 on Arabic readability assessment](https://md.research.elamur.ai/free/en/papers/elmadani-2025-barec-shared-task-2025-arabic/). In Proceedings of the Third Arabic Natural Language Processing Conference, Suzhou, China. Association for Computational Linguistics.
11. Khalid N. Elmadani, Nizar Habash, and Hanada Taha-Thomure. 2025b. [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, pages 16376–16400, Vienna, Austria. Association for Computational Linguistics.
12. 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), pages 359–376, Vienna, Austria. Association for Computational Linguistics.
13. 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.
14. 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. Association for Computational Linguistics.
15. 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. European Language Resources Association.

*Updated 1 November 2026*