Elamur Research⌕
☰
home / papers / 2026 / Syllable Structures Across Arabic Varieties

Syllable Structures Across Arabic Varieties

Summary

Arabic varieties differ considerably in which syllable shapes they permit. Moroccan allows triple-consonant onsets, Maltese has vowel-only syllables, and Juba Arabic lacks long vowels. Yet automatic syllabification research has mostly focused on English. The authors take IPA transcriptions from Wiktionary for nine varieties (Egyptian, Gulf, Hejazi, Juba, Maltese, Moroccan, North Levantine, South Levantine and MSA) and clean them into a "silver standard" resource.

They syllabify the words with Kodner's language-independent SIMPLESYLLABIFY tool, which locates nuclei and places boundaries according to the Maximum Onset Principle. They test it in three settings: fixed default rules, onsets and codas learned jointly across all varieties, and onsets and codas learned separately for each variety. The simple rule-based default proves most accurate. The authors then compare the syllable-type distributions of the varieties using Jensen-Shannon divergence, which reveals three clusters. A targeted error analysis distinguishes genuine algorithm failures from problems in the data.

The work matters because it offers a reusable resource and a quantitative way to compare low-resource, diglossic varieties. Syllable boundaries have also been shown to help downstream tools such as morphological analyzers.

Key points

  • Accuracy by setting: Default reaches 97.05–100%, Per-variety 90.64–100%, and Joint 84.63–94.74%.
  • The syllabifier is SIMPLESYLLABIFY (Kodner, 2016), and the data are IPA transcriptions extracted from Wiktionary.
  • The Jensen-Shannon divergence analysis yields three groups:
    • Egyptian, Hejazi and MSA cluster closely.
    • Levantine and Gulf form a second group.
    • Juba, Maltese and Moroccan are outliers.
  • A cleaned nine-variety dataset is released as a silver standard for Arabic syllabification.
  • Although the method ignores word position, accuracy stays high. This suggests that the data contain few position-dependent syllable restrictions, or that the default rules already deal with them correctly.

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

Cited by

1 paper of our library cites it (of the 140673 whose bibliographies we read); each has a page here.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.vardial-1.21

@inproceedings{qaddoumi2026syllable,
  title = {{Syllable Structures Across Arabic Varieties}},
  author = {Qaddoumi, Abdelrahim and Kodner, Jordan and Khalifa, Salam and Broselow, Ellen and Rambow, Owen},
  booktitle = {Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects},
  year = {2026},
  doi = {10.18653/v1/2026.vardial-1.21},
  url = {https://doi.org/10.18653/v1/2026.vardial-1.21}
}

References

50 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Rajaa Aquil. 2013. Cairne arabic syllable structure though different phonological theories. Open Journal of Modern Linguistics, 3(3):259–267. ↗
  2. International Phonetic Association. 1999. Handbook of the International Phonetic Association: A guide to the use of the International Phonetic Alphabet. Cambridge University Press. find
  3. Abderrafi Benhallam. 1989. Moroccan arabic syllable structure. Revue Langues et Littératures, 8:177–191. find
  4. Ranka Bijeljac-Babic, Josiane Bertoncini, and Jacques Mehler. 1993. How do 4-day-old infants categorize multisyllabic utterances? Developmental psychology, 29(4):711. ↗
  5. Hassan Abdulrashed Bokhari. 2020. A comprehensive analysis of coda clusters in Hijazi Arabic: An optimality-theoretic perspective. Indiana University. find
  6. Abdelaziz Boudlal. 2001. Constraint interaction in the phonology and morphology of Casablanca Moroccan Arabic. Ph.D. thesis, Rutgers University. ↗
  7. Joseph M Brincat. 2005. Maltese–an unusual formula. MED Magazine, 27. find
  8. Ellen Broselow. 2017. Syllable structure in the dialects of arabic. The Routledge handbook of Arabic linguistics, pages 32–47. ↗
  9. Jane Chandlee, Remi Eyraud, Jeffrey Heinz, Adam Jardine, and Jonathan Rawski. 2019. Learning with partially ordered representations. In Proceedings of the 16th Meeting on the Mathematics of Language, pages 91–101, Toronto, Canada. Association for Computational Linguistics. find
  10. Pattarawat Chormai, Ponrawee Prasertsom, Jin Chee-vaprawatdomrong, and Attapol Rutherford. 2020. Syllable-based neural Thai word segmentation. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4619–4637, Barcelona, Spain (Online). International Committee on Computational Linguistics. find
  11. Abdellah Fourtassi, Benjamin Börschinger, Mark Johnson, and Emmanuel Dupoux. 2013. Why is English so easy to segment? In Proceedings of the Fourth Annual Workshop on Cognitive Modeling and Computational Linguistics (CMCL), pages 1–10, Sofia, Bulgaria. Association for Computational Linguistics. find
  12. Bent Fuglede and Flemming Topsoe. 2004. Jensen-shannon divergence and hilbert space embedding. In International symposium onInformation theory, 2004. ISIT 2004. Proceedings., page 31. IEEE. find
  13. Luke Galea and Adam Ussishkin. 2018. Onset clusters, syllable structure and syllabification in Maltese. Language Science Press. ↗
  14. John Goldsmith. 2011. The syllable. The handbook of phonological theory, pages 164–196. find
  15. Ivo Grosse, Pedro Bernaola-Galván, Pedro Carpena, Ramón Román-Roldán, Jose Oliver, and H Eugene Stanley. 2002. Analysis of symbolic sequences using the jensen-shannon divergence. Physical Review E, 65(4):041905. find
  16. Jack Halpern. 2009. Word stress and vowel neutralization in modern standard arabic. In 2nd International Conference on Arabic Language Resources and Tools, pages 1–7. Cairo. find
  17. Rym Hamdi, Salem Ghazali, and Melissa Barkat-Defradas. 2005. Syllable structure in spoken arabic: a comparative investigation. In Eurospeech—9th European Conference on Speech Communication and Technology. find
  18. Bruce Hayes. 2009. Introductory Phonology. Number 23 in Blackwell Textbooks in Linguistics. Wiley-Blackwell. find
  19. Jeffrey Heath. 2020. Moroccan arabic. Arabic and contact-induced change, 1:213. find
  20. Hla Hla Htay and Kavi Narayana Murthy. 2008. Myanmar word segmentation using syllable level longest matching. In Proceedings of the 6th Workshop on Asian Language Resources. find
  21. George N Clements. 1990. The role of the sonority cycle in core syllabification. Papers in laboratory phonology, 1:283–333. ↗
  22. Peter W Jusczyk and Carolyn Derrah. 1987. Representation of speech sounds by young infants. Developmental Psychology, 23(5):648. ↗
  23. David M. Eberhard, Gary F. Simons, and Charles D. Fennig, editors. 2025. Ethnologue: Languages of the World, 28 edition. SIL International, Dallas, Texas. Online edition. find
  24. Daniel Kahn. 2015. Syllable-based generalizations in English phonology. Routledge. ↗
  25. Samira Farwaneh. 2009. Toward a typology of arabic dialects: The role of final consonantality. Journal of Arabic and Islamic studies, 9:82–109. find
  26. Niamh Kelly. 2021. Syllable weight, vowel length and focus in lebanese arabic. Glossa: a journal of general linguistics, 6(1). ↗
  27. Word, Salam Khalifa, Abdelrahim Qaddoumi, Jordan Kodner, and Owen Rambow. 2025. Learning cross-dialectal morphophonology with syllable structure constraints. VarDial 2025, page 157. find
  28. William Fisher. 1996. Tsylb syllabification package. FTP archive. find
  29. Paul Kiparsky. 2003. Syllables and moras in arabic. The syllable in optimality theory, 147:182. ↗
  30. Charles F Ferguson. 1959. 15(2):325–340. Diglossia. find
  31. Jordan Kodner. 2016. Simple Syllabify. find
  32. Constantine Lignos. 2011. Modeling infant word segmentation. In Proceedings of the Fifteenth Conference on Computational Natural Language Learning, pages 29–38, Portland, Oregon, USA. Association for Computational Linguistics. find
  33. Jianfei Ma, Zhaoxin Feng, Emmanuele Chersoni, Huacheng Song, and Ziqi Zhang. 2025. Phonothink: Improving large language models’ reasoning on chinese phonological ambiguities. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 19018–19033. find
  34. Stefano Manfredi and Sara Petrollino. 2013. Juba Arabic. The survey of pidgin and creole languages, 3:54–65. find
  35. Yannick Marchand, Connie R Adsett, and Robert I Damper. 2007. Evaluating automatic syllabification algorithms for english. In Proceedings of the 6th ISCA Workshop on Speech Synthesis. find
  36. John J McCarthy. 1979. On stress and syllabification. Linguistic inquiry, 10(3):443–465. find
  37. Natalie Schrimpf and Gaja Jarosz. 2014. Comparing models of phonotactics for word segmentation. In Proceedings of the 2014 Joint Meeting of SIGMOR-PHON and SIGFSM, pages 19–28, Baltimore, Maryland. Association for Computational Linguistics. find
  38. Elisabeth Selkirk. 1984. On the major class features and syllable theory. Language sound structure. find
  39. Jason Shaw, Adamantios I Gafos, Philip Hoole, and Chakir Zeroual. 2009. Syllabification in Moroccan Arabic: evidence from patterns of temporal stability in articulation. Phonology, 26(1):187–215. ↗
  40. Winston Wu and David Yarowsky. 2021. On pronunciations in wiktionary: Extraction and experiments on multilingual syllabification and stress prediction. In Proceedings of the 14th Workshop on Building and Using Comparable Corpora (BUCC 2021), pages 68–74. find
  41. Tatu Ylönen. 2022. Wiktextract: Wiktionary as machine-readable structured data. In Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 1317–1325, Marseille, France. find
  42. Christian M Meyer and Iryna Gurevych. 2012. Wiktionary: A new rival for expert-built lexicons? Exploring the possibilities of collaborative lexicography. na. find
  43. Catherine Miller. 2006. Juba arabic. In Kees Versteegh, editor, Encyclopedia of Arabic Language and Linguistics, volume 2, pages 517–525. Brill, Leiden. find
  44. Ann M Peters. 1983. The units of language acquisition. Cambridge University Press. find
  45. Hamdi A Qafisheh. 1977. A Short Reference Grammar of Gulf Arabic. ERIC. find
  46. Belal A. Rakhieh. 2009. The Phonology of Ma’ani Arabic: Stratal or Parallel OT. Ph.D. thesis, University of Essex. find
  47. Mike Rosner and Claudia Borg. 2022. D1.25: Report on the Maltese language. Deliverable D1.25 (Public), dated 28-02-2022. find
  48. Karin C Ryding. 2005. A reference grammar of modern standard Arabic. Cambridge university press. ↗
  49. Jenny R Saffran, Richard N Aslin, and Elissa L Newport. 1996. Statistical learning by 8-month-old infants. science, 274(5294):1926–1928. find
  50. Jonathan Sakunkoo and Annabella Sakunkoo. 2025. Lost and found: Computational quality assurance of crowdsourced knowledge on morphological defectivity in wiktionary. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 998–1003. ↗

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/qaddoumi-2026-syllable-structures-across-arabic-varieties/