Elamur Research⌕
☰
home / papers / 2025 / Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks

Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks

Paper · 2025 · Gagan Bhatia, El Moatez Billah Nagoudi, Abdellah El Mekki et al.

Summary

Most text embedding models are built mainly for English and Chinese. They handle Arabic poorly because the language combines rich morphology, many dialects, and culture-specific content. The authors address this with Swan, a pair of Arabic-focused embedding models. Swan-Small is built on ARBERTv2, and Swan-Large is built on ArMistral, an Arabic LLM with further pretraining. The training mix totals about 12.5M examples:

  • human-labelled MSA data from ORCA and mMARCO-ar;
  • dialectal corpora;
  • cross-lingual and multilingual retrieval sets;
  • LLM-generated synthetic retrieval data containing hard negatives, covering MSA, specific domains, and dialects.

To evaluate the models, the authors built ArabicMTEB, a benchmark of 94 datasets across eight task types. It includes cross-lingual retrieval and slices for dialect, domain, and culture. Swan-Large beats Multilingual-E5-large on most Arabic tasks, and Swan-Small beats Multilingual-E5-base. Both are also much cheaper to run than commercial APIs. The work gives Arabic NLP its first broad embedding benchmark, along with open models that handle dialects and cultural content.

Key points

  • ArabicMTEB covers eight task types: retrieval, STS, pair classification, classification, clustering, reranking, bitext mining, and cross-lingual retrieval. Earlier Arabic evaluation relied mostly on STS.
  • The synthetic data was generated with Command R+ and totals 120k MSA examples: 100k general plus 5k each for finance, news, medicine, and legal. A further 15k paragraph-length examples cover Egyptian and Moroccan dialects. The human dialectal data adds 122K samples.
  • Cross-lingual training uses mMARCO in 15 languages. Shared document IDs keep queries and documents aligned, and 100k samples are drawn per language pair. Human data was de-duplicated with Polydedupe.
  • In the ablation (Table 9), adding synthetic MSA data raises the average score from 32.46 to 48.42 for Swan-Small and from 55.39 to 61.91 for Swan-Large. Adding synthetic dialect data lifts Swan-Large dialectal retrieval to 77.03.
  • Embedding 10k documents costs 0.75 with Swan-Large versus 9.88 with OpenAI's model. On the cultural slice, Swan-Large is strongest on Egyptian queries, while Moroccan queries remain harder.

Interesting ideas

  • I1. An LLM is prompted to produce triples of a query, a relevant passage, and a "hard negative" that is related but less useful, which teaches the model fine distinctions rather than easy contrasts.
  • I2. The ablation adds each synthetic subset (MSA, domain, dialect) separately and reports scores per task column, which reveals which data helps which ability, for example dialect data mainly boosting dialect retrieval.
  • I3. The benchmark is deliberately multi-task because a high STS score does not guarantee good clustering or reranking.
  • I4. Cultural test queries were built from country-specific Wikipedia articles on topics such as food, customs, and history, which probes knowledge beyond the language itself.
  • I5. Synthetic paragraphs were generated to compensate for dialect data that is mostly short, noisy social-media text.

For Mova

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

  • I1 (learn): The same prompt pattern could generate near-miss distractor answers, which would serve as negative controls showing whether a reader truly uses the text.
  • I2 (learn): Silver-data sources and teacher tiers could be ablated one at a time, scoring each pipeline stage separately rather than relying on one aggregate.
  • I3 (answer): Readers should be scored across several question types (school tests, maths word problems, fable QA), so that a gain on one type is not mistaken for general understanding.
  • I4 (world): Locale-specific Wikidata and Wikipedia facts could form a test set for the knowledge graph, exposing gaps in regional entities and practices.
  • I5 (tree): Longer, well-formed synthetic texts in an under-represented English variety or register could supplement thin treebank coverage before UD dialect conversion.

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 British ColumbiaVancouver · Canada98 works · 34,805 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.Semitic languages · 2,908 worksEvaluation & benchmarks · 1,220 worksMultilingual & cross-lingual NLP · 828 works

Cite

Cite as Gagan Bhatia, El Moatez Billah Nagoudi, Abdellah El Mekki, Fakhraddin Alwajih and Muhammad Abdul-Mageed. 2025. Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks. Findings of the Association for Computational Linguistics: NAACL 2025.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.findings-naacl.263

@inproceedings{bhatia2025swan,
  title = {{Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks}},
  author = {Gagan Bhatia, El Moatez Billah Nagoudi, Abdellah {El Mekki}, Fakhraddin Alwajih and Muhammad Abdul-Mageed},
  booktitle = {Findings of the Association for Computational Linguistics: NAACL 2025},
  year = {2025},
  doi = {10.18653/v1/2025.findings-naacl.263},
  url = {https://doi.org/10.18653/v1/2025.findings-naacl.263}
}

References

83 references, 59 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. 2023. Improving the domain adaptation of retrieval augmented generation (rag) models for open domain question answering. Transactions of the Association for Computational Linguistics.
  2. Muhammad Abdul-Mageed, Hassan Alhuzali, and Mohamed Elaraby. 2018. You tweet what you speak: A city-level dataset of arabic dialects.
  3. Muhammad Abdul-Mageed, AbdelRahim Elmadany, and El Moatez Billah Nagoudi. 2020a. Arbert & marbert: Deep bidirectional transformers for arabic. ACL-2021 camera ready version. ↗
  4. Muhammad Abdul-Mageed, AbdelRahim Elmadany, and El Moatez Billah Nagoudi. 2021a. Arbert & marbert: Deep bidirectional transformers for arabic. pages 7088–7105.
  5. Muhammad Abdul-Mageed, AbdelRahim Elmadany, and El Moatez Billah Nagoudi. 2021b. 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. ↗
  6. Muhammad Abdul-Mageed, Abdelrahim Elmadany, Chiyu Zhang, Houda Bouamor, Nizar Habash, et al. 2023a. Nadi 2023: The fourth nuanced arabic dialect identification shared task. In Proceedings of ArabicNLP 2023, pages 600–613.
  7. Muhammad Abdul-Mageed, AbdelRahim Elmadany, Chiyu Zhang, El Moatez Billah Nagoudi, Houda Bouamor, and Nizar Habash. 2023b. Nadi 2023: The fourth nuanced arabic dialect identification shared task. pages 600–613.
  8. Muhammad Abdul-Mageed, Amr Keleg, Abdelrahim Elmadany, Chiyu Zhang, Injy Hamed, Walid Magdy, Houda Bouamor, and Nizar Habash. 2024a. Nadi 2024: The fifth nuanced arabic dialect identification shared task. In Proceedings of The Second Arabic https://alliancecan.ca https://arc.ubc.ca/ubc-arc-sockeye Natural Language Processing Conference, pages 709– 728. ↗
  9. Muhammad Abdul-Mageed, Amr Keleg, AbdelRahim Elmadany, Chiyu Zhang, Injy Hamed, Walid Magdy, Houda Bouamor, and Nizar Habash. 2024b. Nadi 2024: The fifth nuanced arabic dialect identification shared task. pages 709–728.
  10. Muhammad Abdul-Mageed, Chiyu Zhang, Houda Bouamor, and Nizar Habash. 2020b. Nadi 2020: The first nuanced arabic dialect identification shared task. pages 97–110.
  11. Muhammad Abdul-Mageed, Chiyu Zhang, AbdelRahim Elmadany, Houda Bouamor, and Nizar Habash. 2021c. Nadi 2021: The second nuanced arabic dialect identification shared task. pages 244–259.
  12. Muhammad Abdul-Mageed, Chiyu Zhang, AbdelRahim Elmadany, Houda Bouamor, and Nizar Habash. 2021d. 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. ↗
  13. Muhammad Abdul-Mageed, Chiyu Zhang, AbdelRahim Elmadany, Houda Bouamor, and Nizar Habash. 2022. Nadi 2022: The third nuanced arabic dialect identification shared task. pages 85–97.
  14. Muhammad Abdul-Mageed, Chiyu Zhang, AbdelRahim Elmadany, and Lyle Ungar. 2020c. Toward micro-dialect identification in diaglossic and code-switched environments. pages 5855–5876. find
  15. Murtadha Ahmed, Saghir Alfasly, Bo Wen, Jamal Ad-deen, Mohammed Ahmed, and Yunfeng Liu. 2024. Alclam: Arabic dialect language model. pages 153– 159.
  16. Asaad Alghamdi, Xinyu Duan, Wei Jiang, Zhenhai Wang, Yimeng Wu, Qingrong Xia, Zhefeng Wang, Yi Zheng, Mehdi Rezagholizadeh, Baoxing Huai, Peilun Cheng, and Abbas Ghaddar. 2023. AraMUS: Pushing the limits of data and model scale for Arabic natural language processing. pages 2883–2894.
  17. Manel Aloui, Hasna Chouikhi, Ghaith Chaabane, Haithem Kchaou, and Chehir Dhaouadi. 2024a. 101 billion arabic words dataset. Preprint, arXiv:2405.01590. ↗
  18. Manel Aloui, Hasna Chouikhi, Ghaith Chaabane, Haithem Kchaou, and Chehir Dhaouadi. 2024b. 101 billion arabic words dataset. Preprint, arXiv:2405.01590. ↗
  19. Fakhraddin Alwajih, Gagan Bhatia, and Muhammad Abdul-Mageed. 2024. Dallah: A dialect-aware multimodal large language model for arabic. Preprint, arXiv:2407.18129. ↗
  20. Mikel Artetxe and Holger Schwenk. 2019. Massively multilingual sentence embeddings for zero-shot cross-lingual transfer and beyond. Transactions of the Association for Computational Linguistics, 7:597–610. ↗
  21. Akari Asai, Jungo Kasai, Jonathan H. Clark, Kenton Lee, Eunsol Choi, and Hannaneh Hajishirzi. 2021. Xor qa: Cross-lingual open-retrieval question answering. Preprint, arXiv:2010.11856. ↗
  22. Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, and Tong Wang. 2018. Ms marco: A human generated machine reading comprehension dataset. Preprint, arXiv:1611.09268. ↗
  23. Ramy Baly, Mitra Mohtarami, James Glass, Lluís Màrquez, Alessandro Moschitti, and Preslav Nakov. 2018. Integrating stance detection and fact checking in a unified corpus. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 21–27.
  24. Gagan Bhatia. 2023. PolyDeDupe. find
  25. Gagan Bhatia, El Moatez Billah Nagoudi, Hasan Cavusoglu, and Muhammad Abdul-Mageed. 2024. Fintral: A family of gpt-4 level multimodal financial large language models. Preprint, arXiv:2402.10986. ↗
  26. Luiz Bonifacio, Vitor Jeronymo, Hugo Queiroz Abonizio, Israel Campiotti, Marzieh Fadaee, Roberto Lotufo, and Rodrigo Nogueira. 2021. mmarco: A multilingual version of the ms marco passage ranking dataset. ↗
  27. Houda Bouamor, Nizar Habash, and Kemal Oflazer. 2014. A multidialectal parallel corpus of arabic. pages 1240–1245.
  28. 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. find
  29. Daniel Cer, Mona Diab, Eneko Agirre, Iñigo Lopez-Gazpio, and Lucia Specia. 2017. SemEval-2017 task 1: Semantic textual similarity multilingual and crosslingual focused evaluation. pages 1–14.
  30. Zhihong Chen, Shuo Yan, Juhao Liang, Feng Jiang, Xiangbo Wu, Fei Yu, Guiming Hardy Chen, Junying Chen, Hongbo Zhang, Li Jianquan, Wan Xiang, and Benyou Wang. 2023. MultilingualSIFT: Multilingual Supervised Instruction Fine-tuning. find
  31. Mathieu Ciancone, Imene Kerboua, Marion Schaeffer, and Wissam Siblini. 2024. Extending the massive text embedding benchmark to french. arXiv preprint arXiv:2405.20468. ↗
  32. Cohere For AI. 2024. c4ai-command-r-plus-08-2024. find
  33. Alexis Conneau, Ruty Rinott, Guillaume Lample, Adina Williams, Samuel R. Bowman, Holger Schwenk, and Veselin Stoyanov. 2018. Xnli: Evaluating cross-lingual sentence representations. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. ↗
  34. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805. ↗
  35. Ibrahim Abu El-Khair. 2016. 1.5 Billion Words Arabic Corpus. arXiv preprint arXiv:1611.04033. ↗
  36. AbdelRahim Elmadany, El Moatez Billah Nagoudi, and Muhammad Abdul-Mageed. 2022. Orca: A challenging benchmark for arabic language understanding.
  37. AbdelRahim Elmadany, ElMoatez Billah Nagoudi, and Muhammad Abdul-Mageed. 2023. ORCA: A challenging benchmark for Arabic language understanding. pages 9559–9586.
  38. Kenneth Enevoldsen, Márton Kardos, Niklas Muennighoff, and Kristoffer Laigaard Nielbo. 2024. The scandinavian embedding benchmarks: Comprehensive assessment of multilingual and monolingual text embedding. arXiv preprint arXiv:2406.02396. ↗
  39. Fangxiaoyu Feng, Yinfei Yang, Daniel Cer, Naveen Arivazhagan, and Wei Wang. 2022. Language-agnostic bert sentence embedding. pages 878–891.
  40. Jack FitzGerald, Christopher Hench, Charith Peris, Scott Mackie, Kay Rottmann, Ana Sanchez, Aaron Nash, Liam Urbach, Vishesh Kakarala, Richa Singh, et al. 2022. Massive: A 1m-example multilingual natural language understanding dataset with 51 typologically-diverse languages. arXiv preprint arXiv:2204.08582. ↗
  41. Gemma-Team, Thomas Mesnard, Cassidy Hardin, Robert Dadashi, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivière, Mihir Sanjay Kale, Juliette Love, Pouya Tafti, Léonard Hussenot, Pier Giuseppe Sessa, Aakanksha Chowdhery, et al. 2024. Gemma: Open models based on gemini research and technology. Preprint, arXiv:2403.08295. ↗
  42. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685. ↗
  43. Huang Huang, Fei Yu, Jianqing Zhu, Xuening Sun, Hao Cheng, Song Dingjie, Zhihong Chen, Mosen Alharthi, Bang An, Juncai He, Ziche Liu, Junying Chen, Jianquan Li, Benyou Wang, Lian Zhang, Ruoyu Sun, Xiang Wan, Haizhou Li, and Jinchao Xu. 2024. Acegpt localizing large language models in arabic. pages 8139–8163.
  44. 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, Kyiv, Ukraine (Online). Association for Computational Linguistics.
  45. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, and William El Sayed. 2023. Mistral 7b. Preprint, arXiv:2310.06825. ↗
  46. Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906. ↗
  47. Amr Keleg, Sharon Goldwater, and Walid Magdy. 2023. Aldi: Quantifying the arabic level of dialectness of text. pages 10597–10611.
  48. Amr Keleg and Walid Magdy. 2023. Arabic dialect identification under scrutiny: Limitations of single-label classification. pages 385–398.
  49. Md Tawkat Islam Khondaker, Abdelrahim Elmadany, Muhammad Abdul-Mageed, VS Laks Lakshmanan, et al. 2022. A benchmark study of contrastive learning for arabic social meaning. In Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP), pages 63–75. ↗
  50. Jinhyuk Lee, Zhuyun Dai, Xiaoqi Ren, Blair Chen, Daniel Cer, Jeremy R. Cole, Kai Hui, Michael Boratko, Rajvi Kapadia, Wen Ding, Yi Luan, Sai Meher Karthik Duddu, Gustavo Hernandez Abrego, Weiqiang Shi, Nithi Gupta, Aditya Kusupati, Prateek Jain, Siddhartha Reddy Jonnalagadda, Ming-Wei Chang, and Iftekhar Naim. 2024. Gecko: Versatile text embeddings distilled from large language models. ↗
  51. Weizhe Lin, Rexhina Blloshmi, Bill Byrne, Adria de Gispert, and Gonzalo Iglesias. 2023. Li-rage: Late interaction retrieval augmented generation with explicit signals for open-domain table question answering. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1557–1566, Toronto, Canada. Association for Computational Linguistics. find
  52. Antoine Louis, Vageesh Saxena, Gijs van Dijck, and Gerasimos Spanakis. 2024. Colbert-xm: A modular multi-vector representation model for zero-shot multilingual information retrieval. ↗
  53. Isabelle Mohr, Markus Krimmel, Saba Sturua, Mohammad Kalim Akram, Andreas Koukounas, Michael Günther, Georgios Mastrapas, Vinit Ravishankar, Joan Fontanals Martínez, Feng Wang, Qi Liu, Ziniu Yu, Jie Fu, Saahil Ognawala, Susana Guzman, Bo Wang, Maximilian Werk, Nan Wang, and Han Xiao. 2024. Multi-task contrastive learning for 8192-token bilingual text embeddings. ↗
  54. Niklas Muennighoff, Hongjin Su, Liang Wang, Nan Yang, Furu Wei, Tao Yu, Amanpreet Singh, and Douwe Kiela. 2024. Generative representational instruction tuning. Preprint, arXiv:2402.09906. ↗
  55. Niklas Muennighoff, Nouamane Tazi, Loïc Magne, and Nils Reimers. 2022. Mteb: Massive text embedding benchmark. arXiv preprint arXiv:2210.07316. ↗
  56. Niklas Muennighoff, Nouamane Tazi, Loic Magne, and Nils Reimers. 2023. Mteb: Massive text embedding benchmark. pages 2014–2037.
  57. Omer Nacar and Anis Koubaa. 2024. Enhancing semantic similarity understanding in arabic nlp with nested embedding learning. ↗
  58. El Moatez Billah Nagoudi, AbdelRahim Elmadany, and Muhammad Abdul-Mageed. 2022. Turjuman: A public toolkit for neural arabic machine translation. pages 1–11.
  59. El Moatez Billah Nagoudi, AbdelRahim Elmadany, Muhammad Abdul-Mageed, and Tariq Alhindi. 2020. Machine generation and detection of Arabic manipulated and fake news. In Proceedings of the Fifth Arabic Natural Language Processing Workshop, pages 69–84, Barcelona, Spain (Online). Association for Computational Linguistics. ↗
  60. El Moatez Billah Nagoudi, AbdelRahim Elmadany, Ahmed El-Shangiti, and Muhammad Abdul-Mageed. 2023a. Dolphin: A challenging and diverse benchmark for Arabic NLG. pages 1404–1422.
  61. El Moatez Billah Nagoudi, AbdelRahim Elmadany, Ahmed El-Shangiti, and Muhammad Abdul-Mageed. 2023b. Dolphin: A challenging and diverse benchmark for arabic nlg. Preprint, arXiv:2305.14989. ↗
  62. OpenAI. 2023. Chatgpt: Optimizing language models for dialogue. OpenAI. https://openai.com/ research/chatgpt. ↗
  63. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, Irwan Bello, Jake Berdine, Gabriel Bernadett-Shapiro, Christopher Berner, Lenny Bogdonoff, et al. 2024. Gpt-4 technical report. Preprint, arXiv:2303.08774. ↗
  64. Rafał Poświata, Sławomir Dadas, and Michał Perełkiewicz. 2024. Pl-mteb: Polish massive text embedding benchmark. arXiv preprint arXiv:2405.10138. ↗
  65. Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084. ↗
  66. Haitham Seelawi, Ibraheem Tuffaha, Mahmoud Gzawi, Wael Farhan, Bashar Talafha, Riham Badawi, Zyad Sober, Oday Al-Dweik, Abed Alhakim Freihat, and Hussein Al-Natsheh. 2021. ALUE: Arabic language understanding evaluation. pages 173–184.
  67. Kirill Semenov, Vilém Zouhar, Tom Kocmi, Dongdong Zhang, Wangchunshu Zhou, and Yuchen Eleanor Jiang. 2023. Findings of the wmt 2023 shared task on machine translation with terminologies. pages 663–671. find
  68. Zhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang, Nan Duan, and Weizhu Chen. 2023. Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy. In Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore. Association for Computational Linguistics.
  69. Xiaoyu Shen, Akari Asai, Bill Byrne, and Adrià de Gispert. 2023. xpqa: Cross-lingual product question answering across 12 languages. Preprint, arXiv:2305.09249. ↗
  70. Feng Shi, Ruifeng Ren, Xiaoying Feng, and Wenjie Li. 2023. Raft: Adapting language model to domain specific rag. arXiv preprint arXiv:2403.10131. ↗
  71. Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram, Michael Günther, Bo Wang, Markus Krimmel, Feng Wang, Georgios Mastrapas, Andreas Koukounas, Nan Wang, and Han Xiao. 2024. jina-embeddings-v3: Multilingual embeddings with task lora. Preprint, arXiv:2409.10173. ↗
  72. Pedro Javier Ortiz Suárez, Benoît Sagot, and Laurent Romary. 2019. Asynchronous Pipeline for Processing Huge Corpora on Medium to Low Resource Infrastructure. In 7th Workshop on the Challenges in the Management of Large Corpora (CMLC-7). Leibniz-Institut für Deutsche Sprache. find
  73. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288. ↗
  74. Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2019. Representation learning with contrastive predictive coding. Preprint, arXiv:1807.03748. ↗
  75. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2024a. Improving text embeddings with large language models. Preprint, arXiv:2401.00368. ↗
  76. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2024b. Multilingual e5 text embeddings: A technical report. ↗
  77. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2024c. Multilingual e5 text embeddings: A technical report. Preprint, arXiv:2402.05672. ↗
  78. Shitao Xiao, Zheng Liu, Peitian Zhang, Niklas Muennighoff, Defu Lian, and Jian-Yun Nie. 2023. C-pack: Packaged resources to advance general chinese embedding. find
  79. Omar F. Zaidan and Chris Callison-Burch. 2014. Arabic dialect identification. Computational Linguistics, 40(1):171–202. ↗
  80. Imad Zeroual, Dirk Goldhahn, Thomas Eckart, and Abdelhak Lakhouaja. 2019. OSIAN: Open Source International Arabic News Corpus - Preparation and Integration into the CLARIN-infrastructure. In Proceedings of the Fourth Arabic Natural Language Processing Workshop, pages 175–182, Florence, Italy. Association for Computational Linguistics. ↗
  81. Xinyu Zhang, Xueguang Ma, Peng Shi, and Jimmy Lin. 2021. Mr. tydi: A multi-lingual benchmark for dense retrieval. pages 127–137. find
  82. Xinyu Zhang, Nandan Thakur, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Mehdi Rezagholizadeh, and Jimmy Lin. 2022. Making a miracl: Multilingual information retrieval across a continuum of languages. Preprint, arXiv:2210.09984. ↗
  83. Xinyu Zhang, Nandan Thakur, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Mehdi Rezagholizadeh, and Jimmy Lin. 2023. Miracl: A multilingual retrieval dataset covering 18 diverse languages. Transactions of the Association for Computational Linguistics, 11:1114–1131. ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/bhatia-2025-swan-arabicmteb-dialect-aware-arabic/