{
 "id": "U4RASD/Muradif",
 "owner": "U4RASD",
 "name": "Muradif",
 "downloads": 84,
 "likes": 5,
 "last_modified": "2026-07-07T08:51:37.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "sentence-similarity"
 ],
 "citation": "@inproceedings{abou-chakra-etal-2026-neoarabert,\n    title = \"{N}eo{A}ra{BERT}: A Modern Foundation Model for {A}rabic Embeddings with Diacritics-Aware Tokenization and {POS}-Targeted Masking\",\n    author = \"Abou Chakra, Chadi  and\n      Hamoud, Hadi Khaled  and\n      Rakan Al Mraikhat, Osama  and\n      Abu Obaida, Qusai  and\n      Ballout, Mohamad  and\n      Zaraket, Fadi\",\n    editor = \"Liakata, Maria  and\n      Moreira, Viviane P.  and\n      Zhang, Jiajun  and\n      Jurgens, David\",\n    booktitle = \"Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026\",\n    month = jul,\n    year = \"2026\",\n    address = \"San Diego, California, United States\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2026.findings-acl.1293/\",\n    doi = \"10.18653/v1/2026.findings-acl.1293\",\n    pages = \"25952--25968\",\n    ISBN = \"979-8-89176-395-1\",\n    abstract = \"We present NeoAraBERT, a state-of-the-art open-source Arabic text-embedding model built on the NeoBERT architecture. We pre-train NeoAraBERT on diverse open-source and internal datasets covering modern standard, classical, and dialectal Arabic. We guided our design choices with Arabic tailored ablation studies including text normalization, light stemming, and diacritics-aware tokenization handling. We also performed more general POS-aware token masking and learning-rate scheduling ablation studies. We benchmarked NeoAraBERT against five top-performing Arabic models on 23",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "8ab9b9d2f4068d7576a9f79f84b4686adfe890f0",
 "stated_evidence": "https://huggingface.co/datasets/U4RASD/Muradif/blob/8ab9b9d2f4068d7576a9f79f84b4686adfe890f0/README.md",
 "file_evidence": "https://huggingface.co/datasets/U4RASD/Muradif/tree/8ab9b9d2f4068d7576a9f79f84b4686adfe890f0",
 "card_nc": false
}