Elamur Research⌕
☰
home / papers / 2022 / Maknuune: A Large Open Palestinian Arabic Lexicon

Maknuune: A Large Open Palestinian Arabic Lexicon

Paper · 2022 · Shahd Salah Uddin Dibas, Christian Khairallah, Nizar Habash et al.

Summary

Palestinian Arabic (PAL), a South Levantine dialect, is widely spoken and increasingly written online, but it has no orthographic standard and few machine-readable resources. Existing PAL dictionaries are small or exist only in print. The authors built Maknuune, an open lexicon focused for now on West Bank sub-dialects. It contains more than 36K entries covering 17K lemmas and 3.7K roots.

Every entry has three parts:

  • diacritized spelling in CODA* conventions,
  • a phonological transcription in CAPHI,
  • an English gloss.

Many entries carry more: broken plurals, templatic feminine forms, phrases, MSA glosses, examples, and notes on usage or location. Annotation decisions were driven by dialect phenomena such as consonant variation, epenthesis, Ta Marbuta allomorphy and blocked plurals.

To test coverage, the authors matched lemmas from the Curras corpus against the lexicon and manually classified a sample of the mismatches. The projected coverage of Curras's lexical lemmas is about 94%. Overlap with MSA and Egyptian lexicons shows that much of Maknuune is distinctly dialectal. The authors describe it as the largest open machine-readable PAL dictionary. It is meant to support taggers, analyzers, speech work and teaching.

Key points

  • Size and structure: over 36K entries, 17K lemmas, 3.7K roots. About 10% of entries are multiword phrases indexed under a main lemma. Roughly two thirds have MSA glosses, examples, or notes.
  • Representation: spelling follows CODA*, pronunciation follows CAPHI, and transliteration uses HSB. Epenthetic variants are stored in their fully epenthesized form, for example xubuz and xubiz for "bread".
  • Coverage on Curras: Curras has 56,004 tokens and 8,315 normalized types; punctuation, digits and proper nouns (23% of tokens) were excluded.
    • Of the remaining entries, 49% match the lexicon exactly.
    • In a 10% sample of non-matches, 74% of types were actually in the lexicon but spelled slightly differently, 20% were out of scope, and 6% were genuinely missing.
    • This gives a projected coverage of about 94% by type and 97% by token.
  • Overlap with other Arabic varieties (at lemma:POSType level):
    • with Calima MSA: 44%, rising to 63% after dediacritization;
    • with Calima EGY: 49%, rising to 75% after dediacritization.
  • Availability: the lexicon is public at palestine-lexicon.org and open to contributions from citizen linguists.

Interesting ideas

  • I1. When lexicon matching against a corpus fails, the authors sample the misses and sort them into spelling variant, out of scope, or truly missing, then project the true coverage; this separates real gaps from normalization noise.
  • I2. Each surface variant gets one canonical stored form (the fully epenthesized one), with the variation documented as a rule rather than listed piecemeal.
  • I3. Blocked plurals are recorded where a paradigm slot is filled by a different word, so the paradigm stays correct instead of being generated by template.
  • I4. Homonyms whose sense is local to one region get separate entries tagged with location, instead of being merged with the shared standard sense.
  • I5. Diacritized and dediacritized overlap are reported side by side, which shows how much apparent similarity disappears once pronunciation detail is kept.

For Mova

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

  • I1 (learn): Evaluations of lemma or frame coverage against a treebank could triage misses the same way, so that convention mismatches are not counted as model or lexicon errors.
  • I2 (tokens): Spelling variants such as British/American forms or informal elisions could map to one canonical lemma by an explicit, explainable rule in the en crate.
  • I3 (tokens): The morphology tables could mark suppletive and blocked forms (e.g. "people" vs "persons") explicitly, so lemmatization and generation never invent a regular form.
  • I4 (world): Ontology entries could carry register or dialect tags for regional senses, letting the world builder pick the right sense from the text's context.
  • I5 (learn): Matching scores could likewise be reported under strict and relaxed normalization, as a control that shows how much agreement comes only from loose matching.

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

🎓University of OxfordOxford · United Kingdom104 works · 157,183 citations🎓New York University Abu DhabiAbu Dhabi · United Arab Emirates122 works · 4,602 citations

Also on the byline: United Nations Relief and Works Agency for Palestine Refugees in the Near East.

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 1Research subjects and languages the work is about.Semitic languages · 2,908 works

Cite

Cite as Shahd Salah Uddin Dibas, Christian Khairallah, Nizar Habash, Omar Fayez Sadi, Tariq Sairafy, Karmel Sarabta and Abrar Ardah. 2022. Maknuune: A Large Open Palestinian Arabic Lexicon. Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2022.wanlp-1.13

@inproceedings{dibas2022maknuune,
  title = {{Maknuune: A Large Open Palestinian Arabic Lexicon}},
  author = {Shahd Salah Uddin Dibas, Christian Khairallah, Nizar Habash, Omar Fayez Sadi, Tariq Sairafy, Karmel Sarabta and Abrar Ardah},
  booktitle = {Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)},
  year = {2022},
  doi = {10.18653/v1/2022.wanlp-1.13},
  url = {https://doi.org/10.18653/v1/2022.wanlp-1.13}
}

References

37 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Muhammad Abdul-Mageed, Chiyu Zhang, AbdelRahim Elmadany, Houda Bouamor, and Nizar Habash. 2021. NADI 2021: The second nuanced Arabic dialect identification shared task. In Proceedings of the Sixth Arabic Natural Language Processing Workshop, pages 244–259, Kyiv, Ukraine (Virtual). Association for Computational Linguistics. ↗
  2. Kathrein Abu Kwaik, Motaz Saad, Stergios Chatzikyriakidis, and Simon Dobnik. 2018. Shami: A corpus of Levantine Arabic dialects. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA).
  3. Karim Al-Haff, Mustafa Jarrar, Tymaa Hammouda, and Fadi Zaraket. 2022. Curras + Baladi: Towards a Levantine Corpus. In Proceedings of the Language Resources and Evaluation Conference, pages 769–778, Marseille, France. European Language Resources Association. ↗
  4. Sarah Alkuhlani and Nizar Habash. 2011. A Corpus for Modeling Morpho-Syntactic Agreement in Arabic: Gender, Number and Rationality. In Proceedings of the Conference of the Association for Computational Linguistics (ACL), Portland, Oregon, USA.
  5. Faisal Alshargi, Shahd Dibas, Sakhar Alkhereyf, Reem Faraj, Basmah Abdulkareem, Sane Yagi, Ouafaa Kacha, Nizar Habash, and Owen Rambow. 2019. Morphologically annotated corpora for seven Arabic dialects: Taizi, sanaani, najdi, jordanian, syrian, iraqi and Moroccan. In Proceedings of the Fourth Arabic Natural Language Processing Workshop, pages 137– 147, Florence, Italy. Association for Computational Linguistics. ↗
  6. Zaid Alyafeai, Maraim Masoud, Mustafa Ghaleb, and Maged S. Al-shaibani. 2022. Masader: Metadata sourcing for Arabic text and speech data resources. In Proceedings of the Language Resources and Evaluation Conference, Marseille, France.
  7. Mark Aronoff. 1976. Word formation in generative grammar. Linguistic Inquiry, Monograph one, The MIT press. find
  8. Ibrahim Bassal. 2012. Hebrew and Aramaic Substrata in Spoken Palestinian Arabic. Mediterranean Language Review, 19:85–104. find
  9. Houda Bouamor, Nizar Habash, Mohammad Salameh, Wajdi Zaghouani, Owen Rambow, Dana Abdulrahim, Ossama Obeid, Salam Khalifa, Fadhl Eryani, Alexander Erdmann, and Kemal Oflazer. 2018. The MADAR Arabic Dialect Corpus and Lexicon. In Proceedings of the Language Resources and Evaluation Conference (LREC), Miyazaki, Japan. find
  10. Kristen Brustad. 2000. The Syntax of Spoken Arabic: A Comparative Study of Moroccan, Egyptian, Syrian, and Kuwaiti Dialects. Georgetown University Press. find
  11. William Cotter and Uri Horesh. 2015. Sociolinguistics of Palestinian Arabic. Encyclopedia of Arabic Language & Linguistics. ↗
  12. Kareem Darwish. 2014. Arabizi Detection and Conversion to Arabic. In Proceedings of the Workshop for Arabic Natural Language Processing (WANLP), pages 217–224, Doha, Qatar. ↗
  13. Mona T Diab, Mohamed Al-Badrashiny, Maryam Aminian, Mohammed Attia, Heba Elfardy, Nizar Habash, Abdelati Hawwari, Wael Salloum, Pradeep Dasigi, and Ramy Eskander. 2014. Tharwa: A Large Scale Dialectal Arabic-Standard Arabic-English Lexicon. In Proceedings of the Language Resources and Evaluation Conference (LREC), pages 3782–3789, Reykjavik, Iceland.
  14. Mahmoud El-Haj. 2020. Habibi - a multi dialect multi national Arabic song lyrics corpus. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 1318–1326, Marseille, France. European Language Resources Association.
  15. Yohanan Elihai. 2004. The olive tree dictionary: A transliterated dictionary of conversational Eastern Arabic (Palestinian). Minerva Jerusalem. find
  16. Charles F Ferguson. 1959. Diglossia. Word, 15(2):325– 340. find
  17. Anis Freiha. 1973. Dictionary of Non-Classical Vocables in the Spoken Arabic of Lebanon. Librairie du Liban. find
  18. Hassan Gadalla, Hanaa Kilany, Howaida Arram, Ashraf Yacoub, Alaa El-Habashi, Amr Shalaby, Krisjanis Karins, Everett Rowson, Robert MacIntyre, Paul Kingsbury, David Graff, and Cynthia McLemore. 1997. CALLHOME Egyptian Arabic transcripts LDC97T19. Web Download. Philadelphia: Linguistic Data Consortium. find
  19. David Graff, Mohamed Maamouri, Basma Bouziri, Sondos Krouna, Seth Kulick, and Tim Buckwalter. 2009. Standard Arabic Morphological Analyzer (SAMA) Version 3.1. Linguistic Data Consortium LDC2009E73. Nizar Habash, Fadhl Eryani, Salam Khalifa, Owen Rambow, Dana Abdulrahim, Alexander Erdmann, Reem Faraj, Wajdi Zaghouani, Houda Bouamor, Nasser Zalmout, Sara Hassan, Faisal Al shargi, Sakhar Alkhereyf, Basma Abdulkareem, Ramy Eskander, Mohammad Salameh, and Hind Saddiki. 2018. Unified guidelines and resources for Arabic dialect orthography. In Proceedings of the Language Resources and Evaluation Conference (LREC), Miyazaki, Japan.
  20. Nizar Habash, Ramy Eskander, and Abdelati Hawwari. 2012. A Morphological Analyzer for Egyptian Arabic. In Proceedings of the Workshop of the Special Interest Group on Computational Morphology and Phonology (SIGMORPHON), pages 1–9, Montréal, Canada.
  21. 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. ↗
  22. Moïn Halloun. 2019. An etymological lexicon of foreign words in Palestinian Arabic : Arabic-Arabic-English : the influence of Greek, Pahlavi, Latin, Persian Syriac, Ottoman language and modern languages in the Palestinian dialect. Bethlehem: Bethlehem University, The Institute of Oral Cultural Heritage of the Palestinians. find
  23. Rukayyah S Herzallah. 1990. Aspects of Palestinian Arabic phonology: A nonlinear approach. Cornell University. find
  24. Simon Hopkins. 1995. sarār "pebbles" — A Canaanite Substrate Word in Palestinian Arabic. Zeitschrift für arabische Linguistik, (30):37–49. find
  25. Mustafa Jarrar, Nizar Habash, Faeq Alrimawi, Diyam Akra, and Nasser Zalmout. 2016. Curras: an annotated corpus for the Palestinian Arabic dialect. Language Resources and Evaluation, pages 1–31. ↗
  26. Salam Khalifa, Nizar Habash, Fadhl Eryani, Ossama Obeid, Dana Abdulrahim, and Meera Al Kaabi. 2018. A morphologically annotated corpus of Emirati Arabic. In Proceedings of the Language Resources and Evaluation Conference (LREC), Miyazaki, Japan.
  27. Salam Khalifa, Sara Hassan, and Nizar Habash. 2017. A morphological analyzer for Gulf Arabic verbs. In Proceedings of the Workshop for Arabic Natural Language Processing (WANLP), Valencia, Spain.
  28. Karima Meftouh, Salima Harrat, Salma Jamoussi, Mourad Abbas, and Kamel Smaili. 2015. Machine translation experiments on PADIC: A parallel Arabic dialect corpus. In Proceedings of the Pacific Asia Conference on Language, Information and Computation.
  29. Arfath Pasha, Mohamed Al-Badrashiny, Mona Diab, Ahmed El Kholy, Ramy Eskander, Nizar Habash, Manoj Pooleery, Owen Rambow, and Ryan Roth. 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.
  30. Frank Rice and Majed Sa’id. 1979. Eastern Arabic. Georgetown University Press. find
  31. Majdi Sawalha, Faisal Alshargi, Abdallah AlShdaifat, Sane Yagi, and Mohammad A. Qudah. 2019. Construction and annotation of the Jordan comprehensive contemporary Arabic corpus (JCCA). In Proceedings of the Fourth Arabic Natural Language Processing Workshop, pages 148–157, Florence, Italy. Association for Computational Linguistics. ↗
  32. Ken-ichi Seto. 1999. Distinguishing metonymy from synecdoche. Metonymy in language and thought, 4:91–120. ↗
  33. June E Shoup. 1980. Phonological aspects of speech recognition. Trends in Speech Recognition, pages 125–138. find
  34. K. Stowasser and M. Ani. 2004. A Dictionary of Syrian Arabic: English-Arabic. G - Reference, Information and Interdisciplinary Subjects Series. Georgetown University Press. find
  35. Dima Taji, Salam Khalifa, Ossama Obeid, Fadhl Eryani, and Nizar Habash. 2018. An Arabic Morphological Analyzer and Generator with Copious Features. In Proceedings of the Fifteenth Workshop on Computational Research in Phonetics, Phonology, and Morphology (SIGMORPHON), pages 140–150.
  36. Raphael Talmon. 2004. 19th century Palestinian Arabic: the testimony of Western travellers. Jerusalem studies in Arabic and Islam, (29):210–280. find
  37. A. Younis and M. Aldrich. 2021. Palestinian Colloquial Arabic Vocabulary. Arabic Vocabulary. Lingualism. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/dibas-2022-maknuune-large-open-palestinian-arabic/