Elamur Research⌕
☰
home / papers / 2026 / Mu'jam Arriyadh: A Comprehensive Lexicon for Contemporary Arabic Language

Mu'jam Arriyadh: A Comprehensive Lexicon for Contemporary Arabic Language

Paper · 2026 · Afrah A. Altamimi, Abdulrahman Alosaimy, Halah Munif Alharbi et al.

Summary

The paper presents Mu'jam Arriyadh, a dictionary of present-day written Arabic from the King Salman Global Academy for Arabic Language. It addresses a gap: existing modern Arabic dictionaries are either built for human readers only or are historical. Earlier projects such as Alshariqah and the Doha Lexicon follow how words changed over time. Mu'jam Arriyadh instead records current usage and is machine-readable from the start.

Entries come from ACCA, a 450-million-word Modern Standard Arabic corpus. ACCA spans over a century and is sampled by region and by genre. Camel Tools assigned a lemma and POS to every token, ambiguous analyses were resolved by hand, and rare forms were dropped.

Entries are organized by lemma rather than by triliteral root, though roots are still recorded. Each entry carries morphological, morpho-syntactic and semantic layers, plus thesaurus-style relations. The schema follows ISO 24,613 (LMF), adapted to fit Arabic.

The result holds over 120,500 words and is free through a web interface and an open API. Its senses are being aligned to Princeton WordNet. According to the authors, no Arabic dictionary before it was built on LMF from the ground up, and this makes it directly usable by NLP systems.

Key points

  • The source corpus is ACCA: 450M words of MSA, with quotas by region and by medium.
    • Region: Gulf and Yemen 30%, Levant and Iraq 25%, Egypt and neighbours 25%, Maghreb 20%.
    • Medium: newspapers 30%, blogs and social media 20%, among other sources.
  • Lemmas and POS were extracted with Camel Tools (Obeid et al., 2020). Ambiguous cases were reviewed manually, and word forms seen fewer than 100 times were excluded.
  • The schema is ISO 24,613 LMF, extended in three ways:
    • synsets with synonym, antonym and hypernym relations;
    • a root field, which LMF itself lacks;
    • "form representation" for regional spellings, common misspellings, abbreviations and acronyms.
  • Dialectal items are admitted only if they are attested in formal writing and traceable to the classical lexical tradition.
  • The lexicon underlies two shared tasks: KSAA-RD (Arabic reverse dictionary, 2023) and KSAA-CAD (reverse dictionary plus WSD, 2024). It is available at dictionary.ksaa.gov.sa, and WordNet sense mapping is in progress.

Interesting ideas

  • I1. A word form enters the lexicon only once it passes a minimum corpus frequency, which keeps the inventory grounded in real recurring usage rather than one-off noise.
  • I2. Spelling variants, misspellings, abbreviations and acronyms are all attached as alternative forms of one lemma entry instead of being separate words.
  • I3. When aligning their senses to Princeton WordNet, the authors explicitly record senses that have no counterpart instead of forcing a nearest match.
  • I4. Rather than bending the data to fit an international schema, they add the one field the standard lacks (root) because it matters for their language.
  • I5. The corpus is built with explicit quotas per region and per genre, so no single source type dominates what the lexicon sees.

For Mova

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

  • I1 (tokens): A frequency floor over a large corpus could decide which lemmas and morphological variants enter the en lexicon, keeping rare junk out of the tagger's dictionary.
  • I2 (tokens): The en lemma table could store British/American spellings, frequent typos and acronyms as forms of one lemma, so the tagger maps them to a single entry explainably.
  • I3 (world): When linking Mova's verb classes and concepts to WordNet/FrameNet/Wikidata, unmapped items could be stored as named gaps, making the ontology's blind spots visible and auditable.
  • I4 (world): Compiled knowledge could keep a standard-shaped core while adding explicit extra fields (e.g., derivational family links like decide/decision) that later reasoning steps need.
  • I5 (learn): Silver-data sampling for witness parsers could use genre quotas (news, fiction, textbooks, web) so training and evaluation sets do not drift toward one register.

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

📚 Shelves 2The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 works

🧭 Topics 1Research subjects and languages the work is about.Semitic languages · 1,485 works

Cite

Cite as Afrah A. Altamimi, Abdulrahman Alosaimy, Halah Munif Alharbi, Hawra Aljasim, Muneera Alhoshan, Amal Almazrua, Hanan Alharbi, Abdulrahman Saeed Alshehri, Bayan M. Almuqhim, Maryam H. Algarny, Yahya A. Asiri, Abdullah I. Alharbi, Saleh Zaidan Albalawi, Fawziah Mohammed Asiri, Sara Ali Alhifthi and Abdullah Alfaifi. 2026. Mu'jam Arriyadh: A Comprehensive Lexicon for Contemporary Arabic Language. Proceedings of the Fifteenth Language Resources and Evaluation Conference.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/5ftvqaetzu76

@inproceedings{altamimi2026mu,
  title = {{Mu'jam Arriyadh: A Comprehensive Lexicon for Contemporary Arabic Language}},
  author = {Afrah A. Altamimi, Abdulrahman Alosaimy, Halah Munif Alharbi, Hawra Aljasim, Muneera Alhoshan, Amal Almazrua, Hanan Alharbi, Abdulrahman Saeed Alshehri, Bayan M. Almuqhim, Maryam H. Algarny, Yahya A. Asiri, Abdullah I. Alharbi, Saleh Zaidan Albalawi, Fawziah Mohammed Asiri, Sara Ali Alhifthi and Abdullah Alfaifi},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/5ftvqaetzu76},
  url = {https://doi.org/10.63317/5ftvqaetzu76}
}

References

9 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Alshammari, W., Almazrua, A., Al Wazrah, A., Almatham, R., Alhoshan, M., & AlOsaimy, A. (2024, August). KSAA-CAD Shared Task: Contemporary Arabic Dictionary for Reverse Dictionary and Word Sense Disambiguation. In N. Habash, H. Bouamor, R. Eskander, N. Tomeh, I. Abu Farha, A. Abdelali, S. Touileb, I. Hamed, Y. Onaizan, B. Alhafni, W. Antoun, S. Khalifa, H. Haddad, I. Zitouni, B. AlKhamissi, & R. Almatham (Eds.), Proceedings of the Second Arabic Natural Language Processing Conference (pp. 677-685). Association for Computational Linguistics. https://doi.org/10.18653/v1/2024.arabicnlp-1.74 ↗
  2. Al-Matham, R., Alshammari, W., AlOsaimy, A., Alhumoud, S., Wazrah, A., Altamimi, A., Alharbi, H., & Alaifi, A. (2023, December). KSAA-RD Shared Task: Arabic Reverse Dictionary. In H. Sawaf, S. El-Beltagy, W. Zaghouani, W. Magdy, A. Abdelali, N. Tomeh, I. Abu Farha, N. Habash, S. Khalifa, A. Keleg, H. Haddad, I. Zitouni, K. Mrini, & R. Almatham (Eds.), Proceedings of ArabicNLP 2023 (pp. 450-460). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.arabicnlp-1.39 ↗
  3. Gharbi, Abdulrahman. (2021). Efforts of the Supreme Council of the Arabic Language in launching the Historical Lexicon of the Arabic Language Project. Djoussour El-maaréfa. Algeria. find
  4. Hamze, Hassan. and Belhbib, Rachid. (2020). Introduction to Doha Historical Lexicon of the Arabic Language. find
  5. Hassan, Tammam. (1994). The meaning and structure of the Arabic Language. Casablanca, Morocco. find
  6. ISO 24613. (2019). Language resource management: Lexical markup framework (LMF). ISO. find
  7. Omar, Ahamed. (2008). Contemporary Arabic Language Lexicon. Cairo, Egypt. Evaluation, Conference Proceedings). European Language Resources Association (ELRA). https://www.aclweb.org/anthology/2020.lrec-1.868v2.pdf ↗
  8. Smrz, O. (2007, June). ElixirFM–implementation of functional arabic morphology. In Proceedings of the 2007 workshop on computational approaches to Semitic languages: common issues and resources (pp. 1-8). — ElixirFM – Implementation of Functional Arabic Morphology
  9. Obeid, O., Zalmout, N., Khalifa, S., Taji, D., Oudah, M., Alhafni, B., Inoue, G., Eryani, F., Erdmann, A., & Habash, N. (2020). CAMeL tools: An open source python toolkit for arabic natural language processing. In N. Calzolari, F. Bechet, P. Blache, K. Choukri, C. Cieri, T. Declerck, S. Goggi, H. Isahara, B. Maegaard, J. Mariani, H. Mazo, A. Moreno, J. Odijk, & S. Piperidis (Eds.), LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings (pp. 7022-7032). (LREC 2020 - 12th International Conference on Language Resources and

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/altamimi-2026-mu-jam-arriyadh-comprehensive-lexicon/