---
title: "A Large-Scale Leveled Readability Lexicon for — Khalil 2020"
description: "The paper tackles the lack of graded vocabulary resources for Modern Standard Arabic (MSA) for native-speaker reading, as part of the SAMER project…"
authors: ["Muhamed Al Khalil", "Nizar Habash", "Zhengyang Jiang"]
year: 2020
venue: "Proceedings of the Twelfth Language Resources and Evaluation Conference"
source: "https://aclanthology.org/2020.lrec-1.373/"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/khalil-2020-large-scale-leveled-readability-lexicon/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/khalil-2020-large-scale-leveled-readability-lexicon/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2020](https://md.research.elamur.ai/free/en/papers/2020/) / A Large-Scale Leveled Readability Lexicon for Standard Arabic

# A Large-Scale Leveled Readability Lexicon for Standard Arabic

**Authors:** [Muhamed Al Khalil](https://md.research.elamur.ai/free/en/authors/muhamed-al-khalil/), [Nizar Habash](https://md.research.elamur.ai/free/en/authors/nizar-habash/), Zhengyang Jiang · **Year:** 2020 · **Venue:** Proceedings of the Twelfth Language Resources and Evaluation Conference · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2020.lrec-1.373/) · [PDF](https://aclanthology.org/2020.lrec-1.373.pdf)

**Citations:** [26](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
The paper tackles the lack of graded vocabulary resources for Modern Standard Arabic (MSA) for native-speaker reading, as part of the SAMER project (Simplification of Arabic Masterpieces for Extensive Reading). The authors argue that pure frequency lists have two problems. First, there is no principled place to draw level boundaries. Second, corpus counts mirror adult and news usage rather than what young readers actually know. They therefore take a hybrid route. They lemmatize a corpus of roughly 11.2M tokens with MADAMIRA and filter out punctuation, OOV items, Latin-script words, proper nouns and abbreviations. Language professionals from three regions of the Arab world then each assign every remaining lemma to one of five readability levels, using guidelines written for this scale. The result is a 26,578-lemma leveled lexicon. Annotator agreement was high, and the large disagreements were mostly explained by regional variation. A comparison with frequency ranks shows where frequency-based leveling helps and where it misleads. The lexicon is released publicly and supports Arabic readability research and educational tools.

## Key points
- The lexicon has 26,578 MSA lemmas, each labelled on a five-level readability scale aimed at native speakers. Every lemma was annotated three times by professionals from three regions.
- Of the 11,188,566 corpus tokens, about 23.1% were filtered out (punctuation, OOV, Latin script, proper nouns, abbreviations and similar). The annotated lemmas cover about 76.9% of tokens.
- Lemmatization uses MADAMIRA, which reports 96.0% accuracy on MSA lemmatization. Lemmatizing matters because undiacritized Arabic words are highly ambiguous.
- The paper illustrates frequency bias with the Buckwalter & Parkinson frequency dictionary. There, 'president' ranks 47th, while 'book', 'reading' and 'library' rank far lower. 'Turtle', a common children's-book word, is absent altogether.
- The resource is released via the CAMeL Lab. Planned extensions cover Arabic dialects (building on MADAR) and non-native learners.

## Interesting ideas
- **Corpus proposes, humans grade:** the corpus only supplies the candidate lemmas, people assign the levels, and frequency is kept as a diagnostic to compare against rather than as the label itself. — For Mova (world): A familiarity or difficulty level per lemma could be stored in the compiled knowledge layer, with human or teacher-assigned levels kept separate from corpus frequency so each value can be traced to its source.
- **Disagreement as signal, not noise:** the authors examined why annotators from different regions disagreed and traced most large gaps to regional usage rather than error, so the disagreement itself became information. — For Mova (learn): When witness parsers or teacher tiers disagree on silver data, the disagreements could be sorted into systematic causes (such as dialect or UD convention differences) before being thrown away as noise.
- **Frequency vs. intuition as a bias probe:** comparing corpus rank against human grading reveals which domain the corpus over-represents, as with news vocabulary outranking everyday words like 'book'. — For Mova (answer): This check could flag vocabulary in fables and school texts that news-heavy training data underweights, pointing to where the readers need extra lexical coverage.
- **Explicit filtering accounting:** the authors report token and type shares for every excluded category (proper nouns, Latin script, abbreviations, OOV), so the scope of the resource is transparent. — For Mova (tokens): The tokenizer and lemmatizer could publish similar per-category statistics, making it explainable what the lemma inventory covers and what it skips.
- **Level boundaries need an external scheme:** the paper argues that a frequency continuum has no natural cut points, so the number of levels and their boundaries must come from a deliberate pedagogical design. — For Mova (back): Generation or simplification aimed at a reading level should use an explicit leveled lexicon as its target rather than raw frequency thresholds, so each word choice can be justified.

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

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

## Cited by

Cited by

26 papers of our library cite it (of the 140884 whose bibliographies we read); 4 of them have a page here, 22 not yet.

- [The SAMER Arabic Text Simplification Corpus](https://md.research.elamur.ai/free/en/papers/alhafni-2024-samer-arabic-text-simplification-corpus/)
- [Lexicon-Enriched Graph Modeling for Arabic Document Readability Prediction](https://md.research.elamur.ai/free/en/papers/elchafei-2025-lexicon-enriched-graph-modeling-arabic/)
- [Benchmarking Arabic Authorship Attribution and Style Transfer with Large Language Models](https://md.research.elamur.ai/free/en/papers/hamed-2026-benchmarking-arabic-authorship-attribution-style/)
- [Arabic Word-level Readability Visualization for Assisted Text Simplification](https://md.research.elamur.ai/free/en/papers/hazim-2022-arabic-word-level-readability-visualization/)

## Cite

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

```bibtex
@inproceedings{khalil2020large,
  title = {{A Large-Scale Leveled Readability Lexicon for Standard Arabic}},
  author = {Khalil, Muhamed Al and Habash, Nizar and Jiang, Zhengyang},
  booktitle = {Proceedings of the Twelfth Language Resources and Evaluation Conference},
  year = {2020},
  url = {https://aclanthology.org/2020.lrec-1.373/}
}
```

- [← previous A Joint Neural Model for Information Extraction with Global Features](https://md.research.elamur.ai/free/en/papers/lin-2020-joint-neural-model-information-extraction/)
- [next → A Lexicon-Based Approach for Detecting Hedges in Informal Text](https://md.research.elamur.ai/free/en/papers/islam-2020-lexicon-based-approach-detecting-hedges/)
- [↑ back to papers of 2020](https://md.research.elamur.ai/free/en/papers/2020/)

## References

29 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Al-Dawsari, M. (2004). The assessment of readability books content (boys-girls) of the first grade of intermediate school according to readability standards. Sultan Qaboos University, Muscat. [find](https://scholar.google.com/scholar?q=Al%2DDawsari%2C+M%2E+%282004%29%2E+The+assessment+of+readability+books+content+%28boys%2Dgirls%29+of+the+first+grade+of+intermediate+school+according+to+readability+standards%2E+Sultan+Qaboos+University%2C+Muscat%2E)
2. Al-Khalifa, H. S. and Al-Ajlan, A. A. (2010). Automatic readability measurements of the Arabic text: An exploratory study. Arabian Journal for Science and Engineering, 35(2 C):103–124. [find](https://scholar.google.com/scholar?q=Al%2DKhalifa%2C+H%2E+S%2E+and+Al%2DAjlan%2C+A%2E+A%2E+%282010%29%2E+Automatic+readability+measurements+of+the+Arabic+text%3A+An+exploratory+study%2E+Arabian+Journal+for+Science+and+Engineering%2C+35%282+C%29%3A103%E2%80%93124%2E)
3. Al Khalil, M., Habash, N., and Saddiki, H. (2017). Simplification of Arabic masterpieces for extensive reading: A project overview. Procedia Computer Science, 117:192– 198. [find](https://scholar.google.com/scholar?q=Al+Khalil%2C+M%2E%2C+Habash%2C+N%2E%2C+and+Saddiki%2C+H%2E+%282017%29%2E+Simplification+of+Arabic+masterpieces+for+extensive+reading%3A+A+project+overview%2E+Procedia+Computer+Science%2C+117%3A192%E2%80%93+198%2E)
4. Al Khalil, M., Saddiki, H., Habash, N., and Alfalasi, L. (2018). A Leveled Reading Corpus of Modern Standard Arabic. In Proceedings of the Language Resources and Evaluation Conference (LREC), Miyazaki, Japan. [find](https://scholar.google.com/scholar?q=Al+Khalil%2C+M%2E%2C+Saddiki%2C+H%2E%2C+Habash%2C+N%2E%2C+and+Alfalasi%2C+L%2E+%282018%29%2E+A+Leveled+Reading+Corpus+of+Modern+Standard+Arabic%2E+In+Proceedings+of+the+Language+Resources+and+Evaluation+Conference+%28LREC%29%2C+Miyazaki)
5. Anderson, J. (1983). Lix and rix: Variations on a little-known readability index. Journal of Reading, 26(6):490–496. [find](https://scholar.google.com/scholar?q=Anderson%2C+J%2E+%281983%29%2E+Lix+and+rix%3A+Variations+on+a+little%2Dknown+readability+index%2E+Journal+of+Reading%2C+26%286%29%3A490%E2%80%93496%2E)
6. Beech, L. W. (2011). 240 Vocabulary Words Kids Need to Know (Series). Scholastic. [find](https://scholar.google.com/scholar?q=Beech%2C+L%2E+W%2E+%282011%29%2E+240+Vocabulary+Words+Kids+Need+to+Know+%28Series%29%2E+Scholastic%2E)
7. Bouamor, H., Habash, N., Salameh, M., Zaghouani, W., Rambow, O., Abdulrahim, D., Obeid, O., Khalifa, S., Eryani, F., Erdmann, A., and Oflazer, K. (2018). The MADAR Arabic Dialect Corpus and Lexicon. In Proceedings of the Language Resources and Evaluation Conference (LREC), Miyazaki, Japan. [find](https://scholar.google.com/scholar?q=Bouamor%2C+H%2E%2C+Habash%2C+N%2E%2C+Salameh%2C+M%2E%2C+Zaghouani%2C+W%2E%2C+Rambow%2C+O%2E%2C+Abdulrahim%2C+D%2E%2C+Obeid%2C+O%2E%2C+Khalifa%2C+S%2E%2C+Eryani%2C+F%2E%2C+Erdmann%2C+A%2E%2C+and+Oflazer%2C+K%2E+%282018%29%2E+The+MADAR+Arabic+Dialect+Corpus+and+Lexicon%2E+I)
8. Brooke, J., Tsang, V., Jacob, D., Shein, F., and Hirst, G. (2012). Building readability lexicons with unannotated corpora. In Proceedings of the First Workshop on Predicting and Improving Text Readability for target reader populations, pages 33–39. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Brooke%2C+J%2E%2C+Tsang%2C+V%2E%2C+Jacob%2C+D%2E%2C+Shein%2C+F%2E%2C+and+Hirst%2C+G%2E+%282012%29%2E+Building+readability+lexicons+with+unannotated+corpora%2E+In+Proceedings+of+the+First+Workshop+on+Predicting+and+Improving+Text+Readabi)
9. Buckwalter, T. and Parkinson, D. (2014). A frequency dictionary of Arabic: Core vocabulary for learners. Routledge. [find](https://scholar.google.com/scholar?q=Buckwalter%2C+T%2E+and+Parkinson%2C+D%2E+%282014%29%2E+A+frequency+dictionary+of+Arabic%3A+Core+vocabulary+for+learners%2E+Routledge%2E)
10. Ehara, Y. (2018). Building an english vocabulary knowledge dataset of japanese english-as-a-second-language learners using crowdsourcing. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). [find](https://scholar.google.com/scholar?q=Ehara%2C+Y%2E+%282018%29%2E+Building+an+english+vocabulary+knowledge+dataset+of+japanese+english%2Das%2Da%2Dsecond%2Dlanguage+learners+using+crowdsourcing%2E+In+Proceedings+of+the+Eleventh+International+Conference+on+Lan)
11. Ferguson, C. F. (1959). Diglossia. Word, 15(2):325–340. [find](https://scholar.google.com/scholar?q=Ferguson%2C+C%2E+F%2E+%281959%29%2E+Diglossia%2E+Word%2C+15%282%29%3A325%E2%80%93340%2E)
12. Forsyth, J. (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=Forsyth%2C+J%2E+%282014%29%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. Fountas, I. C. and Pinnell, G. S. (2006). Leveled books (k-8): Matching texts to readers for effective teaching. Heinemann Educational Books. [find](https://scholar.google.com/scholar?q=Fountas%2C+I%2E+C%2E+and+Pinnell%2C+G%2E+S%2E+%282006%29%2E+Leveled+books+%28k%2D8%29%3A+Matching+texts+to+readers+for+effective+teaching%2E+Heinemann+Educational+Books%2E)
14. Fountas, I. C. and Pinnell, G. S. (2017). Guided reading: Responsive teaching across the grades. Heinemann. [find](https://scholar.google.com/scholar?q=Fountas%2C+I%2E+C%2E+and+Pinnell%2C+G%2E+S%2E+%282017%29%2E+Guided+reading%3A+Responsive+teaching+across+the+grades%2E+Heinemann%2E)
15. Fry, E. (2002). Readability versus leveling. The Reading Teacher, 56(3):286–291, 11. Name - International Reading Association; Random House Inc; Copyright - Copyright International Reading Association Nov 2002; Last updated - 2019-11-23; CODEN - REDTAH; Subject-sTermNotLitGenreText - United States–US; New York. [find](https://scholar.google.com/scholar?q=Fry%2C+E%2E+%282002%29%2E+Readability+versus+leveling%2E+The+Reading+Teacher%2C+56%283%29%3A286%E2%80%93291%2C+11%2E+Name+%2D+International+Reading+Association%3B+Random+House+Inc%3B+Copyright+%2D+Copyright+International+Reading+Association)
16. Habash, N., Soudi, A., and Buckwalter, T. (2007). On Arabic Transliteration. In A. van den Bosch et al., editors, Arabic Computational Morphology: Knowledge-based and Empirical Methods, pages 15–22. Springer, Netherlands. [find](https://scholar.google.com/scholar?q=Habash%2C+N%2E%2C+Soudi%2C+A%2E%2C+and+Buckwalter%2C+T%2E+%282007%29%2E+On+Arabic+Transliteration%2E+In+A%2E+van+den+Bosch+et+al%2E%2C+editors%2C+Arabic+Computational+Morphology%3A+Knowledge%2Dbased+and+Empirical+Methods%2C+pages+15%E2%80%9322%2E+S)
17. Habash, N. Y. (2010). Introduction to Arabic natural language processing, volume 3. Morgan & Claypool Publishers. [find](https://scholar.google.com/scholar?q=Habash%2C+N%2E+Y%2E+%282010%29%2E+Introduction+to+Arabic+natural+language+processing%2C+volume+3%2E+Morgan+%26+Claypool+Publishers%2E)
18. Harb, M. (2019). Hanada’s text leveling system (htls) from text engagement to text engagingness. Academic Journal of Interdisciplinary Studies, 8(2):272–276. [find](https://scholar.google.com/scholar?q=Harb%2C+M%2E+%282019%29%2E+Hanada%E2%80%99s+text+leveling+system+%28htls%29+from+text+engagement+to+text+engagingness%2E+Academic+Journal+of+Interdisciplinary+Studies%2C+8%282%29%3A272%E2%80%93276%2E)
19. Holes, C. (2004). Modern Arabic: Structures, Functions, and Varieties. Georgetown Classics in Arabic Language and Linguistics. Georgetown University Press. [find](https://scholar.google.com/scholar?q=Holes%2C+C%2E+%282004%29%2E+Modern+Arabic%3A+Structures%2C+Functions%2C+and+Varieties%2E+Georgetown+Classics+in+Arabic+Language+and+Linguistics%2E+Georgetown+University+Press%2E)
20. Kilgarriff, A., Charalabopoulou, F., Gavrilidou, M., Johannessen, J. B., Khalil, S., Johansson Kokkinakis, S., Lew, R., Sharoff, S., Vadlapudi, R., and Volodina, E. (2014). Corpus-based vocabulary lists for language learners for nine languages. Language Resources and Evaluation, 48(1):121–163, Mar. [find](https://scholar.google.com/scholar?q=Kilgarriff%2C+A%2E%2C+Charalabopoulou%2C+F%2E%2C+Gavrilidou%2C+M%2E%2C+Johannessen%2C+J%2E+B%2E%2C+Khalil%2C+S%2E%2C+Johansson+Kokkinakis%2C+S%2E%2C+Lew%2C+R%2E%2C+Sharoff%2C+S%2E%2C+Vadlapudi%2C+R%2E%2C+and+Volodina%2C+E%2E+%282014%29%2E+Corpus%2Dbased+vocabulary+lis)
21. Maamouri, M., Graff, D., Bouziri, B., Krouna, S., Bies, A., and Kulick, S. (2010). Standard Arabic morphological analyzer (sama) version 3.1. Linguistic Data Consortium, Catalog No.: LDC2010L01. [find](https://scholar.google.com/scholar?q=Maamouri%2C+M%2E%2C+Graff%2C+D%2E%2C+Bouziri%2C+B%2E%2C+Krouna%2C+S%2E%2C+Bies%2C+A%2E%2C+and+Kulick%2C+S%2E+%282010%29%2E+Standard+Arabic+morphological+analyzer+%28sama%29+version+3%2E1%2E+Linguistic+Data+Consortium%2C+Catalog+No%2E%3A+LDC2010L01%2E)
22. Parker, R., Graff, D., Chen, K., Kong, J., and Maeda, K. (2011). Arabic gigaword fifth edition ldc2011t11. Philadelphia: Linguistic Data Consortium. [find](https://scholar.google.com/scholar?q=Parker%2C+R%2E%2C+Graff%2C+D%2E%2C+Chen%2C+K%2E%2C+Kong%2C+J%2E%2C+and+Maeda%2C+K%2E+%282011%29%2E+Arabic+gigaword+fifth+edition+ldc2011t11%2E+Philadelphia%3A+Linguistic+Data+Consortium%2E)
23. Pasha, A., Al-Badrashiny, M., Diab, M., Kholy, A. E., Eskander, R., Habash, N., Pooleery, M., Rambow, O., and Roth, R. (2014). Madamira: A fast, comprehensive tool for morphological analysis and disambiguation of Arabic. In Proceedings of the Language Resources and Evaluation Conference (LREC), pages 1094–1101, Reykjavik, Iceland. [find](https://scholar.google.com/scholar?q=Pasha%2C+A%2E%2C+Al%2DBadrashiny%2C+M%2E%2C+Diab%2C+M%2E%2C+Kholy%2C+A%2E+E%2E%2C+Eskander%2C+R%2E%2C+Habash%2C+N%2E%2C+Pooleery%2C+M%2E%2C+Rambow%2C+O%2E%2C+and+Roth%2C+R%2E+%282014%29%2E+Madamira%3A+A+fast%2C+comprehensive+tool+for+morphological+analysis+and+disam) [our card](https://md.research.elamur.ai/free/en/papers/lingbulk-2014-pasha-madamira-fast-comprehensive-tool-morphological/)
24. Saddiki, H., Bouzoubaa, K., and Cavalli-Sforza, V. (2015). Text readability for Arabic as a foreign language. In Proceedings of the International Conference of Computer Systems and Applications (AICCSA), pages 1–8, Marrakech, Morocco. [find](https://scholar.google.com/scholar?q=Saddiki%2C+H%2E%2C+Bouzoubaa%2C+K%2E%2C+and+Cavalli%2DSforza%2C+V%2E+%282015%29%2E+Text+readability+for+Arabic+as+a+foreign+language%2E+In+Proceedings+of+the+International+Conference+of+Computer+Systems+and+Applications+%28AICCS)
25. Saddiki, H., Habash, N., Cavalli-Sforza, V., and Al Khalil, M. (2018). Feature optimization for predicting readability of arabic l1 and l2. In Proceedings of the 5th Workshop on Natural Language Processing Techniques for Educational Applications, pages 20–29. [find](https://scholar.google.com/scholar?q=Saddiki%2C+H%2E%2C+Habash%2C+N%2E%2C+Cavalli%2DSforza%2C+V%2E%2C+and+Al+Khalil%2C+M%2E+%282018%29%2E+Feature+optimization+for+predicting+readability+of+arabic+l1+and+l2%2E+In+Proceedings+of+the+5th+Workshop+on+Natural+Language+Proce)
26. Sinclair, J. et al. (2003). Collins COBUILD advanced learner’s English dictionary. Harper Collins Publishers. [find](https://scholar.google.com/scholar?q=Sinclair%2C+J%2E+et+al%2E+%282003%29%2E+Collins+COBUILD+advanced+learner%E2%80%99s+English+dictionary%2E+Harper+Collins+Publishers%2E)
27. Teubert, W. and Cermáková, A. (2007). Corpus linguistics: A short introduction. Continuum. [find](https://scholar.google.com/scholar?q=Teubert%2C+W%2E+and+Cerm%C3%A1kov%C3%A1%2C+A%2E+%282007%29%2E+Corpus+linguistics%3A+A+short+introduction%2E+Continuum%2E)
28. Wynne, M. (2005). Developing linguistic corpora: A guide to good practice, volume 92. Oxbow Books Oxford. [find](https://scholar.google.com/scholar?q=Wynne%2C+M%2E+%282005%29%2E+Developing+linguistic+corpora%3A+A+guide+to+good+practice%2C+volume+92%2E+Oxbow+Books+Oxford%2E)
29. Zipes, J. (2013). Sticks and stones: The troublesome success of children’s literature from Slovenly Peter to Harry Potter. Routledge. [find](https://scholar.google.com/scholar?q=Zipes%2C+J%2E+%282013%29%2E+Sticks+and+stones%3A+The+troublesome+success+of+children%E2%80%99s+literature+from+Slovenly+Peter+to+Harry+Potter%2E+Routledge%2E)