---
title: "Learning Stress in Arabic Low-Resource — Qaddoumi 2026"
description: "The paper addresses automatic prediction of lexical stress in spoken Arabic varieties, which have far fewer resources than Modern Standard Arabic."
authors: ["Abed Qaddoumi", "Salam Khalifa", "Jordan Kodner", "Jeffrey Heinz", "Owen Rambow"]
year: 2026
venue: "Proceedings of the Society for Computation in Linguistics 2026"
source: "https://aclanthology.org/2026.scil-main.24/"
doi: "10.18653/v1/2026.scil-main.24"
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/papers/qaddoumi-2026-learning-stress-arabic-low-resource/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/qaddoumi-2026-learning-stress-arabic-low-resource/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2026](https://md.research.elamur.ai/free/papers/2026/page/3/) / Learning Stress in Arabic Low-Resource Settings

# Learning Stress in Arabic Low-Resource Settings

**Authors:** Abed Qaddoumi, [Salam Khalifa](https://md.research.elamur.ai/free/authors/salam-khalifa/), [Jordan Kodner](https://md.research.elamur.ai/free/authors/jordan-kodner/), Jeffrey Heinz, [Owen Rambow](https://md.research.elamur.ai/free/authors/owen-rambow/) · **Year:** 2026 · **Venue:** Proceedings of the Society for Computation in Linguistics 2026 · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.scil-main.24/) · [PDF](https://aclanthology.org/2026.scil-main.24.pdf) · [DOI 10.18653/v1/2026.scil-main.24](https://doi.org/10.18653/v1/2026.scil-main.24) · [OpenAlex](https://openalex.org/W7166837389)

**Citations:** 0 citations (openalex-snapshot · 2026-10-14)

## Summary
The paper addresses automatic prediction of lexical stress in spoken Arabic varieties, which have far fewer resources than Modern Standard Arabic. The authors study Cairene Egyptian, Ammani Jordanian and Khartoum Sudanese. Each word is reduced to its CV syllable skeleton, and the task is framed as generation: the system takes an unmarked skeleton and returns it with the stressed syllable capitalized. Four systems are compared:
- BUFIA, a grammar-induction algorithm that learns banned substructures and compiles them into finite-state machines
- a character-level transformer transducer
- hand-written rules drawn from descriptive linguistics
- a majority-position baseline

To simulate data scarcity, training sets grow in three ways: by random words, by number of syllables, and by syllable-structure type. The last two test generalization to unseen shapes and longer words. BUFIA generally beats the neural model, most clearly with very little data, and its results vary less across runs. The neural model catches up as data grows and overtakes BUFIA for Egyptian at the largest sizes. The literature-based rules remain the strongest system overall. The study suggests grammar induction is an interpretable, data-efficient option for low-resource phonology.

## Key points
- The authors release new stress-marked datasets for Jordanian and Sudanese Arabic. Native-speaker authors checked the data.
- The rule-based baseline reaches 99.8% (Egyptian), 95.7% (Jordanian) and 86.3% (Sudanese) accuracy. It beats both learned models in most conditions.
- Sampling by structure type is the hardest setting. There, the neural transducer beats the frequency baseline only for Jordanian and Egyptian, and only at the largest training size.
- BUFIA was restricted to a 4-segment window because of its exponential complexity. This causes errors on 4-segment syllables, and the model is sensitive to noise and optionality.
- The neural model sometimes alters or hallucinates syllable structure, for example producing extremely long degenerate outputs. The authors attribute this to framing the task as generation rather than labeling.

*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/shelves/linguistics/)

## Cite

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

```bibtex
@inproceedings{qaddoumi2026learning,
  title = {{Learning Stress in Arabic Low-Resource Settings}},
  author = {Qaddoumi, Abed and Khalifa, Salam and Kodner, Jordan and Heinz, Jeffrey and Rambow, Owen},
  booktitle = {Proceedings of the Society for Computation in Linguistics 2026},
  year = {2026},
  doi = {10.18653/v1/2026.scil-main.24},
  url = {https://doi.org/10.18653/v1/2026.scil-main.24}
}
```

- [← previous KZ-SafetyPrompts: A Kazakh Safety Evaluation Prompt Dataset for Large Language Models](https://md.research.elamur.ai/free/papers/zaghouani-2026-kz-safetyprompts-kazakh-safety-evaluation/)
- [next → LegalSim-PT: Building a Dataset for Legal Document Simplification in Portuguese Leveraging Linguistic Metrics](https://md.research.elamur.ai/free/papers/scalercio-2026-legalsim-pt-building-dataset-legal/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/papers/2026/page/3/)

## References

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

1. James Dickins. 2007. Sudanese Arabic: Phonemat-ics and syllable structure, volume 38. Otto Harrassowitz Verlag. [find](https://scholar.google.com/scholar?q=James+Dickins%2E+2007%2E+Sudanese+Arabic%3A+Phonemat%2Dics+and+syllable+structure%2C+volume+38%2E+Otto+Harrassowitz+Verlag%2E)
2. Qing Dou, Shane Bergsma, Sittichai Jiampojamarn, and Grzegorz Kondrak. 2009. A ranking approach to stress prediction for letter-to-phoneme conversion. In Proceedings of the Joint Conference of the 47th annual meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, pages 118–126. [find](https://scholar.google.com/scholar?q=Qing+Dou%2C+Shane+Bergsma%2C+Sittichai+Jiampojamarn%2C+and+Grzegorz+Kondrak%2E+2009%2E+A+ranking+approach+to+stress+prediction+for+letter%2Dto%2Dphoneme+conversion%2E+In+Proceedings+of+the+Joint+Conference+of+the+47t)
3. Elan Dresher and Jonathan Kaye. 1990. A computational learning model for metrical phonology. Cognition, 34:137–195. [↗](https://doi.org/10.1016/0010-0277(90)90042-i)
4. David M. Eberhard, Gary F. Simons, and Charles D. Fennig, editors. 2025. Ethnologue: Languages of the World, twenty-eighth edition. SIL International, Dallas, Texas. [find](https://scholar.google.com/scholar?q=David+M%2E+Eberhard%2C+Gary+F%2E+Simons%2C+and+Charles+D%2E+Fennig%2C+editors%2E+2025%2E+Ethnologue%3A+Languages+of+the+World%2C+twenty%2Deighth+edition%2E+SIL+International%2C+Dallas%2C+Texas%2E)
5. Ali Abdel-Khalig. 2014. Syllabification and phrasing in three dialects of Sudanese Arabic. Ph.D. thesis, University of Toronto. [find](https://scholar.google.com/scholar?q=Ali+Abdel%2DKhalig%2E+2014%2E+Syllabification+and+phrasing+in+three+dialects+of+Sudanese+Arabic%2E+Ph%2ED%2E+thesis%2C+University+of+Toronto%2E)
6. Khaled Hasan AbuAbbas. 2003. Topics in the phonology of Jordanian Arabic: An optimality theory perspective. University of Kansas. [find](https://scholar.google.com/scholar?q=Khaled+Hasan+AbuAbbas%2E+2003%2E+Topics+in+the+phonology+of+Jordanian+Arabic%3A+An+optimality+theory+perspective%2E+University+of+Kansas%2E)
7. Rasheed Saleem Al-Jarrah. 2002. An optimality-theoretic analysis of stress in the English of native Arabic speakers. Ball State University. [find](https://scholar.google.com/scholar?q=Rasheed+Saleem+Al%2DJarrah%2E+2002%2E+An+optimality%2Dtheoretic+analysis+of+stress+in+the+English+of+native+Arabic+speakers%2E+Ball+State+University%2E)
8. Khalil Ibrahim Al-Sughayer. 1990. Aspects of comparative Jordanian and modern standard Arabic phonology. Michigan State University. [↗](https://doi.org/10.25335/m5qb9vc8k)
9. Enam Al-Wer. 2007. Jordanian arabic (amman). Encyclopedia of Arabic language and linguistics, 2:505– 517. [find](https://scholar.google.com/scholar?q=Enam+Al%2DWer%2E+2007%2E+Jordanian+arabic+%28amman%29%2E+Encyclopedia+of+Arabic+language+and+linguistics%2C+2%3A505%E2%80%93+517%2E)
10. Abdel-Khalig Ali. 2017. Prosodic domains of syllabification in sudanese arabic. Perspectives on Arabic Linguistics XXIX, pages 33–54. [↗](https://doi.org/10.1075/sal.5.03ali)
11. Awn al-Sharif Gasim. 1965. Some aspects of sudanese colloquial arabic. Sudan notes and records, 46:40– 49. [find](https://scholar.google.com/scholar?q=Awn+al%2DSharif+Gasim%2E+1965%2E+Some+aspects+of+sudanese+colloquial+arabic%2E+Sudan+notes+and+records%2C+46%3A40%E2%80%93+49%2E)
12. Diana Geneva, Georgi Shopov, Kostadin Garov, Maria Todorova, Stefan Gerdjikov, and Stoyan Mihov. 2023. Accentor: An explicit lexical stress model for tts systems. In Proc. Interspeech 2023, pages 4848– 4852. [find](https://scholar.google.com/scholar?q=Diana+Geneva%2C+Georgi+Shopov%2C+Kostadin+Garov%2C+Maria+Todorova%2C+Stefan+Gerdjikov%2C+and+Stoyan+Mihov%2E+2023%2E+Accentor%3A+An+explicit+lexical+stress+model+for+tts+systems%2E+In+Proc%2E+Interspeech+2023%2C+pages+4848)
13. John Goldsmith. 1994. A dynamic computational theory of accent systems. In Jennifer Cole and Charles Kisseberth, editors, Perspectives in Phonology, pages 1–28. Stanford: Center for the Study of Language and Information. [find](https://scholar.google.com/scholar?q=John+Goldsmith%2E+1994%2E+A+dynamic+computational+theory+of+accent+systems%2E+In+Jennifer+Cole+and+Charles+Kisseberth%2C+editors%2C+Perspectives+in+Phonology%2C+pages+1%E2%80%9328%2E+Stanford%3A+Center+for+the+Study+of+Langu)
14. John Goldsmith. 2011. The syllable. The handbook of phonological theory, pages 164–196. [find](https://scholar.google.com/scholar?q=John+Goldsmith%2E+2011%2E+The+syllable%2E+The+handbook+of+phonological+theory%2C+pages+164%E2%80%93196%2E)
15. International Phonetic Association. 1999. Handbook of the International Phonetic Association: A guide to the use of the International Phonetic Alphabet. Cambridge University Press. [find](https://scholar.google.com/scholar?q=International+Phonetic+Association%2E+1999%2E+Handbook+of+the+International+Phonetic+Association%3A+A+guide+to+the+use+of+the+International+Phonetic+Alphabet%2E+Cambridge+University+Press%2E)
16. Matthew K Gordon and Harry van der Hulst. 2020. Word-stress systems. [↗](https://doi.org/10.1093/oxfordhb/9780198832232.013.5)
17. Michael Becker. 2022. Cairene arabic stress is local. Radical: A Journal of Phonology, 4:211–247. [find](https://scholar.google.com/scholar?q=Michael+Becker%2E+2022%2E+Cairene+arabic+stress+is+local%2E+Radical%3A+A+Journal+of+Phonology%2C+4%3A211%E2%80%93247%2E)
18. Prahlad Gupta and David Touretzky. 1991. What a perceptron reveals about metrical phonology. In Proceedings of the Thirteenth Annual Conference of the Cognitive Science Society, pages 334–339. [find](https://scholar.google.com/scholar?q=Prahlad+Gupta+and+David+Touretzky%2E+1991%2E+What+a+perceptron+reveals+about+metrical+phonology%2E+In+Proceedings+of+the+Thirteenth+Annual+Conference+of+the+Cognitive+Science+Society%2C+pages+334%E2%80%93339%2E)
19. Ellen Broselow. 2017. Syllable structure in the dialects of arabic. The Routledge handbook of Arabic linguistics, pages 32–47. [↗](https://doi.org/10.4324/9781315147062-3)
20. Ellen Broselow, Su-I Chen, and Marie Huffman. 1997. Syllable weight: convergence of phonology and phonetics. Phonology, 14(1):47–82. [↗](https://doi.org/10.1017/s095267579700331x)
21. Ellen I Broselow. 1976. The phonology of Egyptian Arabic. University of Massachusetts Amherst. [find](https://scholar.google.com/scholar?q=Ellen+I+Broselow%2E+1976%2E+The+phonology+of+Egyptian+Arabic%2E+University+of+Massachusetts+Amherst%2E)
22. 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 Abdel Halim M Hamid. 1984. A descriptive analysis of Sudanese colloquial Arabic phonology. University of Illinois at Urbana-Champaign. [find](https://scholar.google.com/scholar?q=Jane+Chandlee%2C+Remi+Eyraud%2C+Jeffrey+Heinz%2C+Adam+Jardine%2C+and+Jonathan+Rawski%2E+2019%2E+Learning+with+partially+ordered+representations%2E+In+Proceedings+of+the+16th+Meeting+on+the+Mathematics+of+Language%2C+)
23. Bruce Hayes. 1995. Metrical stress theory: Principles and case studies. University of Chicago Press. [find](https://scholar.google.com/scholar?q=Bruce+Hayes%2E+1995%2E+Metrical+stress+theory%3A+Principles+and+case+studies%2E+University+of+Chicago+Press%2E)
24. Bruce Hayes and Colin Wilson. 2008. A maximum entropy model of phonotactics and phonotactic learning. Linguistic inquiry, 39(3):379–440. [↗](https://doi.org/10.1162/ling.2008.39.3.379)
25. Jeffrey Heinz. 2009. On the role of locality in learning stress patterns. Phonology, 26(2):303–351. [↗](https://doi.org/10.1017/s0952675709990145)
26. Bruno Herin, Igor Younes, Enam Al-Wer, and Youssef Al-Sirour. 2021. The classification of bedouin arabic: Insights from northern jordan. Languages, 7(1):1. [↗](https://doi.org/10.3390/languages7010001)
27. Saussan Khalil. 2011. Talk like an Egyptian: Egyptian Arabic as an option for teaching communicative spoken Arabic. [find](https://scholar.google.com/scholar?q=Saussan+Khalil%2E+2011%2E+Talk+like+an+Egyptian%3A+Egyptian+Arabic+as+an+option+for+teaching+communicative+spoken+Arabic%2E)
28. Hanaa Kilany, Hassan Gadalla, Howaida Arram, Ashraf Yacoub, Alaa El-Habashi, and Cynthia McLemore. 2002. Egyptian colloquial arabic lexicon. [https://catalog.ldc.upenn.edu/](https://catalog.ldc.upenn.edu/) LDC99L22. LDC Catalog No. LDC99L22. [↗](https://catalog.ldc.upenn.edu/)
29. Jonathan Rawski. 2021. Structure and Learning in Natural Language. Ph.D. thesis, Stony Brook University. [find](https://scholar.google.com/scholar?q=Jonathan+Rawski%2E+2021%2E+Structure+and+Learning+in+Natural+Language%2E+Ph%2ED%2E+thesis%2C+Stony+Brook+University%2E)
30. James Rogers and Dakotah Lambert. 2019. Some classes of sets of structures definable without quantifiers. In Proceedings of the 16th Meeting on the Mathematics of Language, pages 63–77, Toronto, Canada. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=James+Rogers+and+Dakotah+Lambert%2E+2019%2E+Some+classes+of+sets+of+structures+definable+without+quantifiers%2E+In+Proceedings+of+the+16th+Meeting+on+the+Mathematics+of+Language%2C+pages+63%E2%80%9377%2C+Toronto%2C+Canad)
31. 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. [↗](https://doi.org/10.48448/kwb6-gn59)
32. Jordan Kodner. 2016. Simple Syllabify. [find](https://scholar.google.com/scholar?q=Jordan+Kodner%2E+2016%2E+Simple+Syllabify%2E)
33. P Ladefoged and K Johnson. 2014. A course in phonetics, 7th edn. cengage learning. Inc., Boston. [find](https://scholar.google.com/scholar?q=P+Ladefoged+and+K+Johnson%2E+2014%2E+A+course+in+phonetics%2C+7th+edn%2E+cengage+learning%2E+Inc%2E%2C+Boston%2E)
34. Dakotah Lambert. 2024. System description: A theorem-prover for subregular systems: The language toolkit and its interpreter, plebby. In International Symposium on Functional and Logic Programming, pages 311–328. Springer. [find](https://scholar.google.com/scholar?q=Dakotah+Lambert%2E+2024%2E+System+description%3A+A+theorem%2Dprover+for+subregular+systems%3A+The+language+toolkit+and+its+interpreter%2C+plebby%2E+In+International+Symposium+on+Functional+and+Logic+Programming%2C+pa)
35. Seung Suk Lee, Joe Pater, and Brandon Prickett. 2025. Representing and learning stress in a maxent framework. In Proceedings of the Annual Meetings on Phonology, volume 1. University of Massachusetts Amherst Libraries. [↗](https://doi.org/10.7275/amphonology.3026)
36. Bogdan Ludusan, Stefan Ziegler, and Guillaume Gravier. 2012. Integrating stress information in large vocabulary continuous speech recognition. In INTERSPEECH-Annual Conference of the International Speech Communication Association, page na. [find](https://scholar.google.com/scholar?q=Bogdan+Ludusan%2C+Stefan+Ziegler%2C+and+Guillaume+Gravier%2E+2012%2E+Integrating+stress+information+in+large+vocabulary+continuous+speech+recognition%2E+In+INTERSPEECH%2DAnnual+Conference+of+the+International+Spe)
37. Stefano Manfredi. 2015. Ethnolinguistic identity and language revitalization among the laggorí in the nuba mountains. Multidimensional Change in Sudan (1989–2011): Reshaping Livelihoods, Conflicts and Identities, page 281. [find](https://scholar.google.com/scholar?q=Stefano+Manfredi%2E+2015%2E+Ethnolinguistic+identity+and+language+revitalization+among+the+laggor%C3%AD+in+the+nuba+mountains%2E+Multidimensional+Change+in+Sudan+%281989%E2%80%932011%29%3A+Reshaping+Livelihoods%2C+Conflicts+and)
38. Paul Schachter and Fe T Otanes. 1983. Tagalog reference grammar. Univ of California Press. [find](https://scholar.google.com/scholar?q=Paul+Schachter+and+Fe+T+Otanes%2E+1983%2E+Tagalog+reference+grammar%2E+Univ+of+California+Press%2E)
39. Kari Suomi, Juhani Toivanen, and Riikka Ylitalo. 2009. Finnish sound structure: Phonetics, phonology, phonotactics and prosody. University of Oulu. [find](https://scholar.google.com/scholar?q=Kari+Suomi%2C+Juhani+Toivanen%2C+and+Riikka+Ylitalo%2E+2009%2E+Finnish+sound+structure%3A+Phonetics%2C+phonology%2C+phonotactics+and+prosody%2E+University+of+Oulu%2E)
40. Logan Swanson, Jeffrey Heinz, and Jon Rawski. 2026. Phonotactic learning with structure, not statistics. Linguistic Inquiry. In press. [↗](https://doi.org/10.1162/ling.a.584)
41. Bruce Tesar and Paul Smolensky. 2000. Learnability in Optimalty Theory. MIT Press, Cambridge, MA. [find](https://scholar.google.com/scholar?q=Bruce+Tesar+and+Paul+Smolensky%2E+2000%2E+Learnability+in+Optimalty+Theory%2E+MIT+Press%2C+Cambridge%2C+MA%2E)
42. Daan van Esch, Mason Chua, and Kanishka Rao. 2016. Predicting pronunciations with syllabification and stress with recurrent neural networks. In INTER-SPEECH, pages 2841–2845. [find](https://scholar.google.com/scholar?q=Daan+van+Esch%2C+Mason+Chua%2C+and+Kanishka+Rao%2E+2016%2E+Predicting+pronunciations+with+syllabification+and+stress+with+recurrent+neural+networks%2E+In+INTER%2DSPEECH%2C+pages+2841%E2%80%932845%2E)
43. Inga Vendelin. 2010. Perception of predictable stress: A cross-linguistic investigation. Journal of Phonetics. [find](https://scholar.google.com/scholar?q=Inga+Vendelin%2E+2010%2E+Perception+of+predictable+stress%3A+A+cross%2Dlinguistic+investigation%2E+Journal+of+Phonetics%2E)
44. Kees Versteegh. 2014. Arabic language. Edinburgh University Press. [find](https://scholar.google.com/scholar?q=Kees+Versteegh%2E+2014%2E+Arabic+language%2E+Edinburgh+University+Press%2E)
45. John J McCarthy. 1979. On stress and syllabification. Linguistic inquiry, 10(3):443–465. [find](https://scholar.google.com/scholar?q=John+J+McCarthy%2E+1979%2E+On+stress+and+syllabification%2E+Linguistic+inquiry%2C+10%283%29%3A443%E2%80%93465%2E)
46. Abdel Rahman Mustapha. 1982. La phonologie de l’arabe soudanais (phonématique et accentuation, Tome 1). Ph.D. thesis, PhD thesis: Paris: Université de la Sorbonne Nouvelle. Chao Wang and Stephanie Seneff. Lexical stress modeling for improved speech recognition of spontaneous telephone speech in the jupiter domain. [find](https://scholar.google.com/scholar?q=Abdel+Rahman+Mustapha%2E+1982%2E+La+phonologie+de+l%E2%80%99arabe+soudanais+%28phon%C3%A9matique+et+accentuation%2C+Tome+1%29%2E+Ph%2ED%2E+thesis%2C+PhD+thesis%3A+Paris%3A+Universit%C3%A9+de+la+Sorbonne+Nouvelle%2E+Chao+Wang+and+Stephanie+Sen)
47. Janet CE Watson. 2002. The phonology and morphology of Arabic. Oxford University Press, USA. [↗](https://doi.org/10.1093/oso/9780199257591.001.0001)
48. Janet CE Watson. 2011. Word stress in arabic. [↗](https://doi.org/10.1002/9781444335262.wbctp0124)
49. World Bank. 2024. Population, total — jordan. Accessed 2025-10-05. [find](https://scholar.google.com/scholar?q=World+Bank%2E+2024%2E+Population%2C+total+%E2%80%94+jordan%2E+Accessed+2025%2D10%2D05%2E)
50. Heikki Palva. 1984. A general classification for the arabic dialects spoken in palestine and transjordan. Studia Orientalia Electronica, 55:357–376. [find](https://scholar.google.com/scholar?q=Heikki+Palva%2E+1984%2E+A+general+classification+for+the+arabic+dialects+spoken+in+palestine+and+transjordan%2E+Studia+Orientalia+Electronica%2C+55%3A357%E2%80%93376%2E)
51. Brandon Prickett and Joe Pater. 2025. Learning and generalizing stress patterns with a sequence-to-sequence neural network. Linguistics Vanguard, (0). [↗](https://doi.org/10.1515/lingvan-2024-0252)
52. Abdelrahim Qaddoumi, Jordan Kodner, Salam Khalifa, Ellen Broselow, and Owen Rambow. 2026. Syllable structures across Arabic varieties. In Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects, pages 250–260, Rabat, Morocco. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Abdelrahim+Qaddoumi%2C+Jordan+Kodner%2C+Salam+Khalifa%2C+Ellen+Broselow%2C+and+Owen+Rambow%2E+2026%2E+Syllable+structures+across+Arabic+varieties%2E+In+Proceedings+of+the+13th+Workshop+on+NLP+for+Similar+Languages%2C) [our card](https://md.research.elamur.ai/free/papers/qaddoumi-2026-syllable-structures-across-arabic-varieties/)
53. Shijie Wu, Ryan Cotterell, and Mans Hulden. 2021. Applying the transformer to character-level transduction. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1901–1907. [↗](https://doi.org/10.3929/ethz-b-000518998)
54. Yuxiang Zou, Shichao Liu, Xiang Yin, Haopeng Lin, Chunfeng Wang, Haoyu Zhang, and Zejun Ma. 2021. Fine-grained prosody modeling in neural speech synthesis using tobi representation. In Interspeech, pages 3146–3150. [find](https://scholar.google.com/scholar?q=Yuxiang+Zou%2C+Shichao+Liu%2C+Xiang+Yin%2C+Haopeng+Lin%2C+Chunfeng+Wang%2C+Haoyu+Zhang%2C+and+Zejun+Ma%2E+2021%2E+Fine%2Dgrained+prosody+modeling+in+neural+speech+synthesis+using+tobi+representation%2E+In+Interspeech%2C+pa)