Elamur Research⌕
☰
home / papers / 2025 / Advancing Dialectal Arabic to Modern Standard Arabic Machine Translation

Advancing Dialectal Arabic to Modern Standard Arabic Machine Translation

Summary

Most everyday Arabic is spoken and written in dialects, while most NLP tools are built for Modern Standard Arabic (MSA). This makes dialect-to-MSA (DA–MSA) translation an important bridge. The authors study it for Levantine, Egyptian and Gulf Arabic under low-resource, compute-limited conditions, and take two routes.

The first route needs no training. They compare zero-shot, zero-shot chain-of-thought, few-shot and their own Ara-TEaR prompting across six LLMs. Ara-TEaR is a three-step loop: translate, then critique, then refine. Its critique targets meaning-transfer and adaptation errors.

The second route is an efficient fine-tuning pipeline. It uses LoRA, quantization, data augmentation and joint training on several dialects.

Plain few-shot prompting beat the more elaborate prompting strategies, and GPT-4o was the strongest prompted model. A fine-tuned, quantized Gemma2-9B outperformed zero-shot GPT-4o. Training on all dialects together clearly beat per-dialect models.

The work matters because it shows a usable recipe for dialect-inclusive Arabic MT on modest hardware. Code, data and fine-tuned models are publicly released.

Key points

  • The six prompted LLMs were GPT-3.5, GPT-4o, LLaMA 3.3-70B-Instruct, LLaMA 3.1-405B, Gemma-27B and DeepSeek-V3. Results were scored with BLEU and chrF++ separately for each dialect.
  • Few-shot prompting was the most reliable strategy, and GPT-4o led overall. For example, GPT-4o with few-shot prompting reached 43.16 chrF++ on Egyptian and 40.67 on Levantine.
  • The fine-tuned, quantized Gemma2-9B scored 49.88 chrF++, compared with 44.58 for zero-shot GPT-4o.
  • Joint multi-dialect training gave over 10% higher chrF++ than single-dialect training.
  • 4-bit quantization cut memory use by about 60% and cost less than 1% in quality.
  • Code and data are on GitHub (er-abd/Advancing-DA2MSA-MT), and the models are on Huggingface.

Interesting ideas

  • I1. Ara-TEaR's critique step uses a fixed rubric rather than a vague "improve this" instruction: does the output change, add or drop meaning, and does it fit the target register and handle idioms non-literally? The paper also honestly reports that this loop lost to simple few-shot prompting, a useful warning that refinement loops need a plain baseline. — For Mova (learn): LLM teacher tiers could critique silver parses or frames against a fixed error checklist. Each loop should be accepted only if it beats a no-refinement control.
  • I2. Pooling several related varieties into one training run beat training a separate model per variety by a wide margin. This suggests that shared structure outweighs dialect-specific noise. — For Mova (tree): train the perceptron parser and gparse jointly on several English treebanks or registers instead of per-genre models, with UD dialect conversion making the labels compatible.
  • I3. Aggressive 4-bit quantization kept quality almost intact while cutting memory by more than half. This makes a strong model practical on small hardware. — For Mova (tree): try low-bit quantization of the gparse transformer, checking LAS before and after, to run it cheaply alongside the other witness parsers.
  • I4. The prompts explicitly name the source variety and demand only the final output with no extra text. This simple framing makes LLM outputs cleaner to parse and evaluate. — For Mova (learn): when querying LLM teachers, state the genre or register of the input and require a strict output-only format so the silver data can be machine-checked.
  • I5. Quality is reported with a character-level metric (chrF++) alongside BLEU, which suits morphologically rich outputs where word-level overlap is too harsh. — For Mova (back): score the text → graph → text compressor's round-trips with chrF++ as well as word-level measures, so near-miss inflections are not counted as total failures.

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

Topics: Machine translation

Cited by

8 papers of our library cite it (of the 140884 whose bibliographies we read); 3 of them have a page here, 5 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2507.20301 · arXiv 2507.20301

@misc{alabdullah2025advancing,
  title = {{Advancing Dialectal Arabic to Modern Standard Arabic Machine Translation}},
  author = {Alabdullah, Abdullah and Han, Lifeng and Lin, Chenghua},
  year = {2025},
  doi = {10.48550/arxiv.2507.20301},
  eprint = {2507.20301},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2507.20301}
}

References

46 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abdul-Mageed M, Keleg A, Elmadany A, Zhang C, Hamed I, Magdy W, Bouamor H, Habash N (2024) NADI 2024: The fifth nuanced Arabic dialect identification shared task. In: Habash N, Bouamor H, Eskander R, Tomeh N, Abu Farha I, Abdelali A, Touileb S, Hamed I, Onaizan Y, Alhafni B, Antoun W, Khalifa S, Haddad H, Zitouni I, AlKhamissi B, Almatham R, Mrini K (eds) Proceedings of the Second Arabic Natural Language Processing Conference, Association for Computational Linguistics, Bangkok, Thailand, pp 709–728, DOI 10.18653/v1/2024.arabicnlp-1.79, URL https://aclanthology.org/2024.arabicnlp-1.79/ ↗
  2. Al-Khalifa H, Darwish K, Mubarak H, Ali M, Elsayed T (eds) (2024) Proceedings of the 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT) with Shared Tasks on Arabic LLMs Hallucination and Dialect to MSA Machine Translation @ LREC-COLING 2024, ELRA and ICCL, Torino, Italia, URL https://aclanthology.org/2024.osact-1.0/ ↗
  3. Alahmari SS (2024) Sirius Translators at OSACT6 2024 shared task: Fintuning ara-t5 models for translating Arabic dialectal text to Modern Standard Arabic. In: Al-Khalifa H, Darwish K, Mubarak H, Ali M, Elsayed T (eds) Proceedings of the 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT) with Shared Tasks on Arabic LLMs Hallucination and Dialect to MSA Machine Translation @ LREC-COLING 2024, ELRA and ICCL, Torino, Italia, pp 117–123, URL https://aclanthology.org/2024.osact-1.15/ Alhafni B, Al-Towaity S, Fawzy Z, Nassar F, Eryani F, Bouamor H, Habash N (2024) Exploiting dialect identification in automatic dialectal text normalization. In: Habash N, Bouamor H, Eskander R, Tomeh N, Abu Farha I, Abdelali A, Touileb S, Hamed I, Onaizan Y, Alhafni B, Antoun W, Khalifa S, Haddad H, Zitouni I, AlKhamissi B, Almatham R, Mrini K (eds) Proceedings of the Second Arabic Natural Language Processing Conference, Association for Computational Linguistics, Bangkok, Thailand, pp 42–54, DOI 10.18653/v1/2024.arabicnlp-1.4, URL https://aclanthology.org/2024. arabicnlp-1.4/ Atwany H, Rabih N, Mohammed I, Waheed A, Raj B (2024) Osact 2024 task 2: Arabic dialect to msa translation. In: OSACT 2024 Workshop, pp 98–103 ↗ our card
  4. Baniata LH, Ampomah IKE, Park SY (2021) A transformer-based neural machine translation model for arabic dialects that utilizes subword units. Sensors 21(19):6509, DOI 10.3390/s21196509, URL https://doi.org/10.3390/s21196509 ↗
  5. Bavaresco A, Bernardi R, Bertolazzi L, Elliott D, Fernández R, Gatt A, Ghaleb E, Giulianelli M, Hanna M, Koller A, Martins A, Mondorf P, Neplenbroek V, Pezzelle S, Plank B, Schlangen D, Suglia A, Surikuchi AK, Takmaz E, Testoni A (2025) LLMs instead of human judges? a large scale empirical study across 20 NLP evaluation tasks. In: Che W, Nabende J, Shutova E, Pilehvar MT (eds) Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Association for Computational Linguistics, Vienna, Austria, pp 238– 255, DOI 10.18653/v1/2025.acl-short.20, URL https://aclanthology.org/2025.acl-short.20/ Bouamor H, Habash N, Salameh M, Zaghouani W, Rambow O, Abdulrahim D, Obeid O, Khalifa S, Eryani F, Erdmann A, Oflazer K (2018) The MADAR Arabic dialect corpus and lexicon. In: Calzolari N, Choukri K, Cieri C, Declerck T, Goggi S, Hasida K, Isahara H, Maegaard B, Mariani J, Mazo H, Moreno A, Odijk J, Piperidis S, Tokunaga T (eds) Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), European Language Resources Association (ELRA), Miyazaki, Japan, URL https://aclanthology.org/L18-1535/ ↗ our card
  6. Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler D, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D (2020) Language models are few-shot learners. In: Larochelle H, Ranzato M, Hadsell R, Balcan M, Lin H (eds) Advances in Neural Information Processing Systems, Curran Associates, Inc., vol 33, pp 1877–1901, URL https://proceedings.neurips.cc/paper_files/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf ↗
  7. Buckwalter T (2004) Buckwalter arabic morphological analyzer version 2.0. Linguistic Data Consortium, LDC2004L02, DOI 10.35111/050q-5r95, URL https://catalog.ldc.upenn.edu/LDC2004L02 ↗
  8. Caillaut G, Qader R, Nakhlé M, Liu J, Barthélemy JG (2024) Scaling laws of decoder-only models on the multilingual machine translation task. In: Proceedings of the Ninth Conference on Machine Translation (WMT) find
  9. Chen B, Yi F, Varró D (2023) Prompting or fine-tuning? a comparative study of large language models for taxonomy construction. In: 2023 ACM/IEEE International Conference on Model Driven Engineering Languages and Systems Companion (MODELS-C), pp 588–596, DOI 10.1109/MODELS-C59198.2023.00097 ↗
  10. Chung HW, Hou L, Longpre S, Zoph B, Tai Y, Fedus W, Li Y, Wang X, Dehghani M, Brahma S, Webson A, Gu SS, Dai Z, Suzgun M, Chen X, Chowdhery A, Castro-Ros A, Pellat M, Robinson K, Valter D, Narang S, Mishra G, Yu A, Zhao V, Huang Y, Dai A, Yu H, Petrov S, Chi EH, Dean J, Devlin J, Roberts A, Zhou D, Le QV, Wei J (2024) Scaling instruction-finetuned language models. J Mach Learn Res 25(1) find
  11. Cui M, Gao P, Liu W, Luan J, Wang B (2025) Multilingual machine translation with open large language models at practical scale: An empirical study. In: Chiruzzo L, Ritter A, Wang L (eds) Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Association for Computational Linguistics, Albuquerque, New Mexico, pp 5420–5443, DOI 10.18653/v1/2025.naacl-long.280, URL https://aclanthology.org/2025.naacl-long.280/ ↗
  12. Demidova A, Atwany H, Rabih N, Sha’ban S (2024) Arabic train at NADI 2024 shared task: LLMs’ ability to translate Arabic dialects into Modern Standard Arabic. In: Habash N, Bouamor H, Eskander R, Tomeh N, Abu Farha I, Abdelali A, Touileb S, Hamed I, Onaizan Y, Alhafni B, Antoun W, Khalifa S, Haddad H, Zitouni I, AlKhamissi B, Almatham R, Mrini K (eds) Proceedings of the Second Arabic Natural Language Processing Conference, Association for Computational Linguistics, Bangkok, Thailand, pp 729–734, DOI 10.18653/v1/2024.arabicnlp-1.80, URL https://aclanthology.org/2024.arabicnlp-1.80/ Eberhard DM, Simons GF, Fennig CD (eds) (2023) Ethnologue: Languages of the World, 26th edn. SIL International, Dallas, Texas, URL https://www.ethnologue.com/insights/ethnologue200 ↗
  13. Exploding Topics (2025) Number of parameters in gpt-4. https://explodingtopics.com/blog/gpt-parameters ↗
  14. Feng Z, Zhang Y, Li H, Wu B, Liao J, Liu W, Lang J, Feng Y, Wu J, Liu Z (2025) TEaR: Improving LLM-based machine translation with systematic self-refinement. In: Chiruzzo L, Ritter A, Wang L (eds) Findings of the Association for Computational Linguistics: NAACL 2025, Association for Computational Linguistics, Albuquerque, New Mexico, pp 3922–3938, DOI 10.18653/v1/2025.findings-naacl.218, URL https://aclanthology.org/2025.findings-naacl.218/ Habash N, Rambow O (2005) Arabic tokenization, part-of-speech tagging and morphological disambiguation in one fell swoop. In: Knight K, Ng HT, Oflazer K (eds) Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05), Association for Computational Linguistics, Ann Arbor, Michigan, pp 573–580, DOI 10.3115/1219840.1219911, URL https://aclanthology.org/P05-1071/ ↗ our card
  15. Habash N, Diab M, Rambow O (2012) Conventional orthography for dialectal Arabic. In: Calzolari N, Choukri K, Declerck T, Doğan MU, Maegaard B, Mariani J, Moreno A, Odijk J, Piperidis S (eds) Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12), European Language Resources Association (ELRA), Istanbul, Turkey, pp 711–718, URL https://aclanthology.org/L12-1328/ ↗ our card
  16. Hadj Mohamed N, Rassem M, Han L, Nenadic G (2023) AlphaMWE-Arabic: Arabic edition of multilingual parallel corpora with multiword expression annotations. In: Mitkov R, Angelova G (eds) Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, INCOMA Ltd., Shoumen, Bulgaria, Varna, Bulgaria, pp 448–457, URL https://aclanthology.org/2023.ranlp-1.50/ ↗
  17. Hamed MM, Hreden M, Hennara K, Aldallal Z, Chrouf S, AlModhayan S (2025) Lahjawi: Arabic cross-dialect translator. In: Ezzini S, Alami H, Berrada I, Benlahbib A, El Mahdaouy A, Lamsiyah S, Derrouz H, Haddad Haddad A, Jarrar M, El-Haj M, Mitkov R, Rayson P (eds) Proceedings of the 4th Workshop on Arabic Corpus Linguistics (WACL-4), Association for Computational Linguistics, Abu Dhabi, UAE, pp 12–24, URL https://aclanthology.org/2025.wacl-1.2/ ↗
  18. Han L, Smeaton A, Jones G (2021) Translation quality assessment: A brief survey on manual and automatic methods. In: Proceedings for the First Workshop on Modelling Translation: Translatology in the Digital Age, pp 15–33 find
  19. Han L, Gladkoff S, Erofeev G, Sorokina I, Galiano B, Nenadic G (2024) Neural machine translation of clinical text: an empirical investigation into multilingual pre-trained language models and transfer-learning. Frontiers in Digital Health 6:1211,564 find
  20. Howard J, Ruder S (2018) Universal language model fine-tuning for text classification. In: Gurevych I, Miyao Y (eds) Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Association for Computational Linguistics, Melbourne, Australia, pp 328–339, DOI 10.18653/v1/P18-1031, URL https://aclanthology.org/P18-1031/ Ibrahim M (2024) CUFE at NADI 2024 shared task: Fine-tuning llama-3 to translate from Arabic dialects to Modern Standard Arabic. In: Habash N, Bouamor H, Eskander R, Tomeh N, Abu Farha I, Abdelali A, Touileb S, Hamed I, Onaizan Y, Alhafni B, Antoun W, Khalifa S, Haddad H, Zitouni I, AlKhamissi B, Almatham R, Mrini K (eds) Proceedings of the Second Arabic Natural Language Processing Conference, Association for Computational Linguistics, Bangkok, Thailand, pp 769–773, DOI 10.18653/v1/2024. arabicnlp-1.87, URL https://aclanthology.org/2024.arabicnlp-1.87/ ↗
  21. Johnson M, Schuster M, Le QV, Krikun M, Wu Y, Chen Z, Thorat N, Viégas F, Wattenberg M, Corrado G, Hughes M, Dean J (2017) Google’s multilingual neural machine translation system: Enabling zero-shot translation. Transactions of the Association for Computational Linguistics 5:339–351, DOI 10.1162/tacl a 00065, URL https://aclanthology.org/Q17-1024/ ↗
  22. Kadaoui K, Magdy SM, Waheed A, Khondaker MTI, El-Shangiti AO, Nagoudi EMB, Abdul-Mageed M (2023) TARJAMAT: Evaluation of bard and Chat-GPT on machine translation of ten Arabic varieties. In: Sawaf H, El-Beltagy S, Zaghouani W, Magdy W, Abdelali A, Tomeh N, Abu Farha I, Habash N, Khalifa S, Keleg A, Haddad H, Zitouni I, Mrini K, Almatham R (eds) find
  23. Proceedings of ArabicNLP 2023, Association for Computational Linguistics, Singapore (Hybrid), pp 52–75, DOI 10.18653/v1/2023.arabicnlp-1.6, URL https://aclanthology.org/2023.arabicnlp-1.6/ ↗ our card
  24. Khalifa M, Abdul-Mageed M, Shaalan K (2021) Self-training pre-trained language models for zero- and few-shot multi-dialectal Arabic sequence labeling. In: Merlo P, Tiedemann J, Tsarfaty R (eds) Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, Association for Computational Linguistics, Online, pp 769–782, DOI 10.18653/v1/2021.eacl-main.65, URL https://aclanthology.org/2021.eacl-main.65/ ↗
  25. Khered A, Benkhedda Y, Batista-Navarro R (2025) Dial2MSA-verified: A multi-dialect Arabic social media dataset for neural machine translation to Modern Standard Arabic. In: Ezzini S, Alami H, Berrada I, Benlahbib A, El Mahdaouy A, Lamsiyah S, Derrouz H, Haddad Haddad A, Jarrar M, El-Haj M, Mitkov R, Rayson P (eds) Proceedings of the 4th Workshop on Arabic Corpus Linguistics (WACL-4), Association for Computational Linguistics, Abu Dhabi, UAE, pp 50–62, URL https://aclanthology.org/2025.wacl-1.6/ ↗
  26. Klementiev A, Irvine A, Callison-Burch C, Yarowsky D (2012) Toward statistical machine translation without parallel corpora. In: Daelemans W (ed) Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, Association for Computational Linguistics, Avignon, France, pp 130–140, URL https://aclanthology.org/E12-1014/ ↗
  27. Koehn P, Hoang H, Birch A, Callison-Burch C, Federico M, Bertoldi N, Cowan B, Shen W, Moran C, Zens R, Dyer C, Bojar O, Constantin A, Herbst E (2007) Moses: Open source toolkit for statistical machine translation. In: Ananiadou S (ed) Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics Companion Volume Proceedings of the Demo and Poster Sessions, Association for Computational Linguistics, Prague, Czech Republic, pp 177–180, URL https://aclanthology.org/P07-2045/ ↗
  28. Krubiński M, Sellat H, Saleh S, Pospı́šil A, Zemánek P, Pecina P (2023) Multi-parallel corpus of North Levantine Arabic. In: Sawaf H, El-Beltagy S, Zaghouani W, Magdy W, Abdelali A, Tomeh N, Abu Farha I, Habash N, Khalifa S, Keleg A, Haddad H, Zitouni I, Mrini K, Almatham R (eds) Proceedings of ArabicNLP 2023, Association for Computational Linguistics, Singapore (Hybrid), pp 411–417, DOI 10.18653/v1/2023.arabicnlp-1.34, URL https://aclanthology.org/2023.arabicnlp-1.34/ ↗
  29. Kwaik KA, Saad M, Chatzikyriakidis S, Dobnik S (2018) A lexical distance study of arabic dialects. Procedia Computer Science 142:2–13, DOI https://doi.org/10.1016/j.procs.2018.10.456, URL https://www.sciencedirect. com/science/article/pii/S1877050918321562, arabic Computational Linguistics LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436– 444, DOI 10.1038/nature14539 ↗
  30. Liu P, Yuan W, Fu J, Jiang Z, Hayashi H, Neubig G (2023) Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM Comput Surv 55(9), DOI 10.1145/3560815, URL https://doi.org/10.1145/3560815 ↗ our card
  31. Lommel A, Popovic M, Burchardt A (2012) Multidimensional quality metrics (mqm): A framework for declaring and describing translation quality metrics. In: Proceedings of Translating and the Computer 34 (TC34) find
  32. Lommel A, Gladkoff S, Melby A, Wright SE, Strandvik I, Gasova K, Vaasa A, Benzo A, Marazzato Sparano R, Foresi M, Innis J, Han L, Nenadic G (2024) The multi-range theory of translation quality measurement: MQM scoring models and statistical quality control. In: Martindale M, Campbell J, Savenkov K, Goel S (eds) Proceedings of the 16th Conference of the Association for Machine Translation in the Americas (Volume 2: Presentations), Association for Machine Translation in the Americas, Chicago, USA, pp 75–94, URL https://aclanthology.org/2024.amta-presentations.6/ ↗
  33. Luccioni S, Jernite Y, Strubell E (2024) Power hungry processing: Watts driving the cost of ai deployment? In: Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency, Association for Computing Machinery, New York, NY, USA, FAccT ’24, p 85–99, DOI 10.1145/3630106.3658542, URL https://doi.org/10.1145/3630106.3658542 ↗
  34. Mager M, Bhatnagar R, Neubig G, Vu NT, Kann K (2023) Neural machine translation for the indigenous languages of the Americas: An introduction. In: Mager M, Ebrahimi A, Oncevay A, Rice E, Rijhwani S, Palmer A, Kann K (eds) Proceedings of the Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP), Association for Computational Linguistics, Toronto, Canada, pp 109–133, DOI 10.18653/v1/2023.americasnlp-1.13, URL https://aclanthology.org/2023. americasnlp-1.13/ Mousi B, Durrani N, Ahmad F, Hasan MA, Hasanain M, Kabbani T, Dalvi F, Chowdhury SA, Alam F (2025) AraDiCE: Benchmarks for dialectal and cultural capabilities in LLMs. In: Rambow O, Wanner L, Apidianaki M, Al-Khalifa H, Eugenio BD, Schockaert S (eds) Proceedings of the 31st International Conference on Computational Linguistics, Association for Computational Linguistics, Abu Dhabi, UAE, pp 4186–4218, URL https://aclanthology.org/2025.coling-main.283/ ↗
  35. Naik D, Naik I, Naik N (2024) Decoder-only transformers: The brains behind generative ai, large language models and large multimodal models. In: Naik N, Jenkins P, Prajapat S, Grace P (eds) Contributions Presented at The International Conference on Computing, Communication, Cybersecurity and AI, July 3–4, 2024, London, UK, Springer Nature Switzerland, Cham, pp 315–331 find
  36. Papineni K, Roukos S, Ward T, Zhu WJ (2002) Bleu: a method for automatic evaluation of machine translation. In: Isabelle P, Charniak E, Lin D (eds) Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Philadelphia, Pennsylvania, USA, pp 311–318, DOI 10.3115/1073083.1073135, URL https://aclanthology.org/P02-1040/ ↗ our card
  37. Pasha A, Al-Badrashiny M, Diab M, El Kholy A, Eskander R, Habash N, Pooleery M, Rambow O, Roth R (2014) MADAMIRA: A fast, comprehensive tool for morphological analysis and disambiguation of Arabic. In: Calzolari N, Choukri K, Declerck T, Loftsson H, Maegaard B, Mariani J, Moreno A, Odijk J, Piperidis S (eds) Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), European Language Resources Association (ELRA), Reykjavik, Iceland, pp 1094–1101, URL https://aclanthology.org/L14-1479/ ↗ our card
  38. Popović M (2017) chrF++: words helping character n-grams. In: Bojar O, Buck C, Chatterjee R, Federmann C, Graham Y, Haddow B, Huck M, Yepes AJ, Koehn P, Kreutzer J (eds) Proceedings of the Second Conference on Machine Translation, Association for Computational Linguistics, Copenhagen, Denmark, pp 612–618, DOI 10.18653/v1/W17-4770, URL https://aclanthology.org/W17-4770/ ↗ our card
  39. Post M (2018) A call for clarity in reporting BLEU scores. In: Bojar O, Chatterjee R, Federmann C, Fishel M, Graham Y, Haddow B, Huck M, Yepes AJ, Koehn P, Monz C, Negri M, Névéol A, Neves M, Post M, Specia L, Turchi M, Verspoor K (eds) Proceedings of the Third Conference on Machine Translation: Research Papers, Association for Computational Linguistics, Brussels, Belgium, pp 186–191, DOI 10.18653/v1/W18-6319, URL https://aclanthology.org/W18-6319/ ↗ our card
  40. Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou Y, Li W, Liu PJ (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res 21(1) find
  41. Rei R, Stewart C, Farinha AC, Lavie A (2020) COMET: A neural framework for MT evaluation. In: Webber B, Cohn T, He Y, Liu Y (eds) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics, Online, pp 2685–2702, DOI 10.18653/v1/2020.emnlp-main.213, URL https://aclanthology.org/2020.emnlp-main.213/ ↗ our card
  42. Sajjad H, Abdelali A, Mubarak H, Al-Kaabi M, Bouamor H (2023) Dialects in the age of large language models: A case study on arabic. In: Findings of the Association for Computational Linguistics: EMNLP 2023, Association for Computational Linguistics Taori R, Gulrajani I, Zhang T, Dubois Y, Li X, Guestrin C, Liang P, Hashimoto TB (2023) Stanford alpaca: An instruction-following llama model. https://github.com/tatsu-lab/stanford_alpaca ↗
  43. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Lu, Polosukhin I (2017) Attention is all you need. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R (eds) Advances in Neural Information Processing Systems, Curran Associates, Inc., vol 30, URL https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf ↗
  44. Wei J, Wang X, Schuurmans D, Bosma M, Ichter B, Xia F, Chi EH, Le QV, Zhou D (2022) Chain-of-thought prompting elicits reasoning in large language models. In: Proceedings of the 36th International Conference on Neural Information Processing Systems, Curran Associates Inc., Red Hook, NY, USA, NIPS ’22 find our card
  45. Yin Hong K, Han L, Batista-Navarro R, Nenadic G (2024) Cantonmt: Investigating back-translation and model-switch mechanisms for cantonese-english neural machine translation. ACM Trans Asian Low-Resour Lang Inf Process DOI 10.1145/3698236, URL https://doi.org/10.1145/3698236, just Accepted Zhang T, Kishore V, Wu F, Weinberger KQ, Artzi Y (2019) BERTScore: Evaluating text generation with BERT. arXiv preprint arXiv:190409675 URL https://arxiv.org/abs/1904.09675 ↗
  46. Zhao W, Wang X, Liu J, Zhang T, Zhang B, Fung P (2023) Exploring the limits of zero-shot transfer for arabic dialect processing with llms. arXiv preprint arXiv:231002245 find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/alabdullah-2025-advancing-dialectal-arabic-modern-standard/