Elamur Research⌕
☰
home / papers / 2026 / From FusHa to Folk: Exploring Cross-Lingual Transfer in Arabic Language Models

From FusHa to Folk: Exploring Cross-Lingual Transfer in Arabic Language Models

Paper · 2026 · Abdulmuizz Khalak, Abderrahmane Issam and Gerasimos Spanakis

Summary

Arabic language models are mostly pretrained on Modern Standard Arabic (MSA, FusHa) and are expected to work on the spoken dialects (DA), whose distance from MSA varies widely. The authors test whether that expectation holds. They compare MSA-centric, mixed (MIX), multi-dialect (Multi-DA) and single-dialect encoders in two ways. The first is functional: linear probes on frozen layer outputs for POS tagging, NER and sentiment analysis (SA) on dialect datasets, with each model scored at its best layer. The second is structural: layer-wise linear CKA between MSA and DA models, computed on parallel MADAR sentences. Both measures are then related to a geographic distance proxy and to the amount of pretraining data. Transfer from MSA does happen, but it is uneven. It weakens as dialects lie farther away, and the size of this effect depends on how much data a model saw. Pooling all dialects in one model also causes negative interference for well-resourced dialects. The results challenge the assumption that one MSA-based model can serve the whole Arabic continuum.

Key points

  • Three probing tasks are used. POS and NER are probed at the token level, and SA uses mean-pooled sentence vectors fed to a softmax linear classifier.
  • Representational similarity is measured with linear CKA on parallel sentences from the MADAR corpus. Yemen serves as the geographic anchor standing in for MSA.
  • The MSA encoder usually wins on NER and POS. The authors explain this by shared syntax and by dialect speakers code-switching to MSA for named entities. Dialect models tend to win on SA, where idioms, non-standard spelling and negation matter.
  • Dialect-specific models such as EgyBERT and DziriBERT beat general models on high-resource dialects like Egyptian and Saudi. General models win on low-resource ones like Lebanese and Jordanian.
  • DziriBERT shows high CKA similarity to MSA without a matching advantage in probing. This gap between structural and functional similarity echoes Davari et al. (2023).
  • No Gulf NER dataset existed, so the authors created proxy labels on MADAR with an existing NER model. Regional datasets were divided by country using automatic dialect identification.

Interesting ideas

  • I1. Pair an extrinsic test (probing accuracy) with an intrinsic one (CKA on parallel input), and treat any disagreement as a finding, since high similarity need not mean useful features.
  • I2. Model language varieties as a continuum with a measurable distance from an anchor, then check whether transfer performance falls off along that distance.
  • I3. Break results down by task type to find where a shared standard carries over: syntax and entities transfer well, while sentiment, idioms and negation do not.
  • I4. When gold labels are missing for a variety, run an existing model over a parallel corpus to make proxy labels, and state the noise this adds.
  • I5. Mixing many varieties can hurt the well-resourced ones, so the authors suggest region-specific parameters.

For Mova

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

  • I1 (learn): When comparing witness parsers, report how much their internal representations agree separately from how well they score on tasks. A parser that looks similar to the others but adds no task value should not count as an independent witness.
  • I2 (tree): Order English genres or dialects (news, forum text, transcribed speech, older prose) by their distance from the main training treebank. Then plot how parser LAS degrades along that ordering to decide where UD dialect conversion or extra treebanks are most needed.
  • I3 (frames): Expect the tree layer to transfer across registers more easily than pragmatics. Give irony, negation scope and idiom handling in prag their own register-specific tests instead of assuming parser robustness is enough.
  • I4 (learn): Silver data built this way should be marked by its origin and checked against negative controls. That way, any gains measured on proxy-labelled slices are not mistaken for real improvements.
  • I5 (learn): Before folding new domains into one parser model, compare per-domain scores against a single-domain baseline. Where interference appears, add small domain-specific components.

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

🎓Maastricht UniversityMaastricht · Netherlands6 works · 605 citations

 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 3Research subjects and languages the work is about.Language models & pretraining · 3,320 worksSemitic languages · 2,908 worksMultilingual & cross-lingual NLP · 828 works

Cite

Cite as Abdulmuizz Khalak, Abderrahmane Issam and Gerasimos Spanakis. 2026. From FusHa to Folk: Exploring Cross-Lingual Transfer in Arabic Language Models. arXiv:2602.09826.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2602.09826 · arXiv 2602.09826

@misc{khalak2026fusha,
  title = {{From FusHa to Folk: Exploring Cross-Lingual Transfer in Arabic Language Models}},
  author = {Abdulmuizz Khalak, Abderrahmane Issam and Gerasimos Spanakis},
  year = {2026},
  doi = {10.48550/arxiv.2602.09826},
  eprint = {2602.09826},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2602.09826}
}

References

65 references, 41 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Amine Abdaoui, Mohamed Berrimi, Mourad Oussalah, and Abdelouahab Moussaoui. 2021. Dziribert: a pre-trained language model for the algerian dialect. CoRR, abs/2109.12346. ↗
  2. Ahmed Abdelali, Nadir Durrani, Fahim Dalvi, and Hassan Sajjad. 2022. Post-hoc analysis of Arabic transformer models. In Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 91–103, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
  3. Abdulkareem Alsudais, Wafa Alotaibi, and Faye Alo-mary. 2022. Similarities between arabic dialects: Investigating geographical proximity. Information Processing & Management, 59(1):102770. ↗
  4. Muhammad Abdul-Mageed, AbdelRahim Elmadany, and El Moatez Billah Nagoudi. 2021. ARBERT & MARBERT: Deep bidirectional transformers for Arabic. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 7088–7105, Online. Association for Computational Linguistics. ↗
  5. Mohamed Aly and Amir Atiya. 2013. LABR: A large scale Arabic book reviews dataset. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 494–498, Sofia, Bulgaria. Association for Computational Linguistics. ↗
  6. Hossameddine Abouzahr and Mohammed Abouzahr. 2025. Lexical and lexical-semantic comparisons of classical arabic and dialects. International Journal of Arabic Linguistics, 11:66–98. ↗
  7. Reem AlYami and Rabah Al-Zaidy. 2022. Weakly and semi-supervised learning for Arabic text classification using monodialectal language models. In Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP), pages 260–272, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
  8. Ibrahim Abu Farha and Walid Magdy. 2022. The effect of Arabic dialect familiarity on data annotation. In Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP), pages 399–408, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
  9. Wissam Antoun, Fady Baly, and Hazem Hajj. 2020. AraBERT: Transformer-based model for Arabic language understanding. In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pages 9–15, Marseille, France. European Language Resource Association. ↗
  10. 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).
  11. Wissam Antoun, Fady Baly, and Hazem Hajj. 2021. AraGPT2: Pre-trained transformer for Arabic language generation. In Proceedings of the Sixth Arabic Natural Language Processing Workshop, pages 196–207, Kyiv, Ukraine (Virtual). Association for Computational Linguistics. ↗
  12. Ashraf Ahmad, Mohammad Azzeh, Eman Alnagi, Qasem Abu Al-Haija, Dana Halabi, Abdullah Aref, and Yousef AbuHour. 2024. Hate speech detection in the arabic language: corpus design, construction, and evaluation. Frontiers in Artificial Intelligence, Volume 7 - 2024. ↗
  13. Belen Alastruey, João Maria Janeiro, Alexandre Allauzen, Maha Elbayad, Loïc Barrault, and Marta R. Costa-jussà. 2025. Interference matrix: Quantifying cross-lingual interference in transformer encoders. Preprint, arXiv:2508.02256. ↗
  14. Mashael AlDuwais, Hend Al-Khalifa, and Abdulmalik AlSalman. 2024. CLEANANERCorp: Identifying and correcting incorrect labels in the ANERcorp dataset. In 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, pages 13–19, Torino, Italia. ELRA and ICCL. find
  15. Areeb Alowisheq, Nora Al-Twairesh, Mawaheb Al-tuwaijri, Afnan Almoammar, Alhanouf Alsuwailem, Tarfa Albuhairi, Wejdan Alahaideb, and Sarah Alhu-moud. 2021. Marsa: Multi-domain arabic resources for sentiment analysis. IEEE Access, 9:142718– 142728. ↗
  16. Mikel Artetxe, Sebastian Ruder, and Dani Yogatama. 2020. On the cross-lingual transferability of monolingual representations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4623–4637, Online. Association for Computational Linguistics.
  17. Ankur Bapna and Orhan Firat. 2019. Simple, scalable adaptation for neural machine translation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1538– 1548, Hong Kong, China. Association for Computational Linguistics. ↗
  18. Zakaria Benmounah, Abdennour Boulesnane, Abde-ladim Fadheli, and Mustapha Khial. 2023. Sentiment analysis on algerian dialect with transformers. Applied Sciences, 13(20). ↗
  19. 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 Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA). find
  20. Ahmad Muhammad Boyi, Muhammad Badamasi Yusuf, and Mustapha Muhammad Isa. 2024. The relevance of arabic dialects and their diversity across the arab world. Journal of Arts and Sociological Research, 6. find
  21. Juuso Eronen, Michal Ptaszynski, and Fumito Masui. 2023. Zero-shot cross-lingual transfer language selection using linguistic similarity. Information Processing & Management, 60(3):103250. ↗
  22. J. K. Chambers and Peter Trudgill. 1998. Dialectology, page 3–12. Cambridge Textbooks in Linguistics. Cambridge University Press. find
  23. Charles A. Ferguson. 1959. 15(2):325–340. find
  24. Tyler A. Chang, Catherine Arnett, Zhuowen Tu, and Ben Bergen. 2024. When is multilinguality a curse? language modeling for 250 high- and low-resource languages. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 4074–4096, Miami, Florida, USA. Association for Computational Linguistics.
  25. Kamel Gaanoun, Abdou Mohamed Naira, Anass Allak, and Imade Benelallam. 2025. Darijabert: a step forward in nlp for the written moroccan dialect. International Journal of Data Science and Analytics, 20(2):917–929. ↗
  26. Alexis Conneau, German Kruszewski, Guillaume Lample, Loïc Barrault, and Marco Baroni. 2018a. What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2126–2136, Melbourne, Australia. Association for Computational Linguistics. ↗
  27. Alexis Conneau, Ruty Rinott, Guillaume Lample, Adina Williams, Samuel Bowman, Holger Schwenk, and Veselin Stoyanov. 2018b. XNLI: Evaluating cross-lingual sentence representations. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2475–2485, Brussels, Belgium. Association for Computational Linguistics. ↗
  28. Abdelhalim Hafedh Dahou and Mohamed Amine Cheragui. 2023. Dzner: A large algerian named entity recognition dataset. Natural Language Processing Journal, 3:100005. ↗
  29. Fahim Dalvi, Avery Nortonsmith, Anthony Bau, Yonatan Belinkov, Hassan Sajjad, Nadir Durrani, and James Glass. 2019. Neurox: A toolkit for analyzing individual neurons in neural networks. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01):9851–9852. ↗
  30. Kareem Darwish, Hamdy Mubarak, Ahmed Abdelali, Mohamed Eldesouki, Younes Samih, Randah Alharbi, Mohammed Attia, Walid Magdy, and Laura Kallmeyer. 2018. Multi-dialect Arabic POS tagging: A CRF approach. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA).
  31. MohammadReza Davari, Stefan Horoi, Amine Natik, Guillaume Lajoie, Guy Wolf, and Eugene Belilovsky. 2023. Reliability of CKA as a similarity measure in deep learning. In The Eleventh International Conference on Learning Representations. ↗
  32. Niama Elkhbir, Urchade Zaratiana, Nadi Tomeh, and Thierry Charnois. 2023. Cross-dialectal named entity recognition in Arabic. In Proceedings of ArabicNLP 2023, pages 140–149, Singapore (Hybrid). Association for Computational Linguistics. Diglossia.
  33. WORD, Nizar Habash, Muhammed AbuOdeh, Dima Taji, Reem Faraj, Jamila El Gizuli, and Omar Kallas. 2022. Camel treebank: An open multi-genre Arabic dependency treebank. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 2672–2681, Marseille, France. European Language Resources Association.
  34. Nizar Habash and Owen Rambow. 2006. MAGEAD: A morphological analyzer and generator for the Arabic dialects. In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, pages 681–688, Sydney, Australia. Association for Computational Linguistics. ↗
  35. John Hewitt and Christopher D. Manning. 2019. A structural probe for finding syntax in word representations. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4129–4138, Minneapolis, Minnesota. Association for Computational Linguistics. ↗
  36. Go Inoue, Bashar Alhafni, Nurpeiis Baimukan, Houda Bouamor, and Nizar Habash. 2021. The interplay of variant, size, and task type in Arabic pre-trained language models. In Proceedings of the Sixth Arabic Natural Language Processing Workshop, pages 92– 104, Kyiv, Ukraine (Virtual). Association for Computational Linguistics.
  37. Mustafa Jarrar, Mohammed Khalilia, and Sana Ghanem. 2022. Wojood: Nested Arabic named entity corpus and recognition using BERT. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 3626–3636, Marseille, France. European Language Resources Association.
  38. Mouad Jbel, Mourad Jabrane, Imad Hafidi, and Abdul-mutallib Metrane. 2024. Sentiment analysis dataset in moroccan dialect: bridging the gap between arabic and latin scripted dialect. Lang. Resour. Eval., 59(2):1401–1430. ↗
  39. Karthikeyan K, Zihan Wang, Stephen Mayhew, and Dan Roth. 2020. Cross-lingual ability of multilingual bert: An empirical study. In International Conference on Learning Representations. ↗
  40. Amr Keleg, Sharon Goldwater, and Walid Magdy. 2023. ALDi: Quantifying the Arabic level of dialectness of text. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 10597–10611, Singapore. Association for Computational Linguistics.
  41. Salam Khalifa, Nizar Habash, Dana Abdulrahim, and Sara Hassan. 2016. A large scale corpus of Gulf Arabic. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 4282–4289, Portorož, Slovenia. European Language Resources Association (ELRA).
  42. Rania Kora and Ammar Mohammed. 2019. Corpus on Arabic Egyptian tweets. find
  43. Simon Kornblith, Mohammad Norouzi, Honglak Lee, and Geoffrey Hinton. 2019. Similarity of neural network representations revisited. In Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 3519–3529. PMLR. ↗
  44. Kathrein Abu Kwaik, Motaz Saad, Stergios Chatzikyriakidis, and Simon Dobnik. 2018. A lexical distance study of arabic dialects. Procedia Computer Science, 142:2–13. Arabic Computational Linguistics. find
  45. Wuwei Lan, Yang Chen, Wei Xu, and Alan Ritter. 2020. An empirical study of pre-trained transformers for Arabic information extraction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4727–4734, Online. Association for Computational Linguistics.
  46. Yu-Hsiang Lin, Chian-Yu Chen, Jean Lee, Zirui Li, Yuyan Zhang, Mengzhou Xia, Shruti Rijhwani, Junxian He, Zhisong Zhang, Xuezhe Ma, Antonios Anastasopoulos, Patrick Littell, and Graham Neubig. 2019. Choosing transfer languages for cross-lingual learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3125–3135, Florence, Italy. Association for Computational Linguistics. ↗
  47. Nelson F. Liu, Matt Gardner, Yonatan Belinkov, Matthew E. Peters, and Noah A. Smith. 2019. Linguistic knowledge and transferability of contextual representations. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1073–1094, Minneapolis, Minnesota. Association for Computational Linguistics.
  48. Hanane Nour Moussa and Asmaa Mourhir. 2023. Darnercorp: An annotated named entity recognition dataset in the moroccan dialect. Data in Brief, 48:109234. ↗
  49. Hala Mulki, Hatem Haddad, Chedi Bechikh Ali, and Halima Alshabani. 2019. L-HSAB: A Levantine Twitter dataset for hate speech and abusive language. In Proceedings of the Third Workshop on Abusive Language Online, pages 111–118, Florence, Italy. Association for Computational Linguistics.
  50. Jonathan Owens. 2006. A Linguistic History of Arabic. Oxford University Press. ↗
  51. Fred Philippy, Siwen Guo, and Shohreh Haddadan. 2023. Identifying the correlation between language distance and cross-lingual transfer in a multilingual representation space. In Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP, pages 22–29, Dubrovnik, Croatia. Association for Computational Linguistics. find
  52. Tiago Pimentel, Josef Valvoda, Rowan Hall Maudslay, Ran Zmigrod, Adina Williams, and Ryan Cotterell. 2020. Information-theoretic probing for linguistic structure. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4609–4622, Online. Association for Computational Linguistics.
  53. Telmo Pires, Eva Schlinger, and Dan Garrette. 2019. How multilingual is multilingual BERT? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4996–5001, Florence, Italy. Association for Computational Linguistics. ↗
  54. Faisal Qarah. 2024a. Egybert: A large language model pretrained on egyptian dialect corpora. Preprint, arXiv:2408.03524. ↗
  55. Faisal Qarah. 2024b. Saudibert: A large language model pretrained on saudi dialect corpora. Preprint, arXiv:2405.06239. ↗
  56. Djamé Seddah, Farah Essaidi, Amal Fethi, Matthieu Futeral, Benjamin Muller, Pedro Javier Ortiz Suárez, Benoît Sagot, and Abhishek Srivastava. 2020. Building a user-generated content North-African Arabizi treebank: Tackling hell. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1139–1150, Online. Association for Computational Linguistics. find
  57. Neha Sengupta, Sunil Kumar Sahu, Bokang Jia, Satheesh Katipomu, Haonan Li, Fajri Koto, William Marshall, Gurpreet Gosal, Cynthia Liu, Zhiming Chen, Osama Mohammed Afzal, Samta Kamboj, Onkar Pandit, Rahul Pal, Lalit Pradhan, Zain Muhammad Mujahid, Massa Baali, Xudong Han, Sondos Mahmoud Bsharat, and 13 others. 2023. Jais and jais-chat: Arabic-centric foundation and instruction-tuned open generative large language models. Preprint, arXiv:2308.16149. ↗
  58. Skyler Seto, Maartje Ter Hoeve, Richard He Bai, Natalie Schluter, and David Grangier. 2025. Training bilingual LMs with data constraints in the targeted language. In Findings of the Association for Computational Linguistics: ACL 2025, pages 19096–19122, Vienna, Austria. Association for Computational Linguistics. find
  59. Guokan Shang, Hadi Abdine, Ahmad Chamma, Amr Mohamed, Mohamed Anwar, Abdelaziz Bounhar, Omar El Herraoui, Preslav Nakov, Michalis Vazirgiannis, and Eric P. Xing. 2025. Nile-chat: Egyptian language models for Arabic and Latin scripts. In Proceedings of The Third Arabic Natural Language Processing Conference, pages 306–322, Suzhou, China. Association for Computational Linguistics.
  60. Ian Tenney, Dipanjan Das, and Ellie Pavlick. 2019a. BERT rediscovers the classical NLP pipeline. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4593– 4601, Florence, Italy. Association for Computational Linguistics. ↗
  61. Ian Tenney, Patrick Xia, Berlin Chen, Alex Wang, Adam Poliak, R. Thomas McCoy, Najoung Kim, Benjamin Van Durme, Samuel R. Bowman, Dipanjan Das, and Ellie Pavlick. 2019b. What do you learn from context? probing for sentence structure in contextualized word representations. In International Conference on Learning Representations. ↗
  62. Kees Versteegh. 2014. The Arabic Language, ned - new edition, 2 edition. Edinburgh University Press. find
  63. Zirui Wang, Zachary C. Lipton, and Yulia Tsvetkov. 2020. On negative interference in multilingual models: Findings and a meta-learning treatment. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4438–4450, Online. Association for Computational Linguistics.
  64. Shijie Wu and Mark Dredze. 2019. Beto, bentz, becas: The surprising cross-lingual effectiveness of BERT. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 833–844, Hong Kong, China. Association for Computational Linguistics. ↗
  65. Shijie Wu and Mark Dredze. 2020. Are all languages created equal in multilingual BERT? In Proceedings of the 5th Workshop on Representation Learning for NLP, pages 120–130, Online. Association for Computational Linguistics.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/khalak-2026-fusha-folk-exploring-cross-lingual/