{
    "Name": "ArabicDialectHub",
    "Volume": 552.0,
    "Unit": "sentences",
    "License": "MIT License",
    "Link": "https://github.com/saleml/arabic-dialect-hub",
    "HF_Link": "",
    "Year": 2024,
    "Domain": [
        "other"
    ],
    "Form": "text",
    "Collection_Style": [
        "LLM generated",
        "human annotation"
    ],
    "Description": "ArabicDialectHub: cross-dialectal learning resource.",
    "Ethical_Risks": "Low",
    "Provider": [
        "Mohamed Bin Zayed University of Artificial Intelligence"
    ],
    "Derived_From": [],
    "Paper_Title": "ArabicDialectHub: A Cross-Dialectal Arabic Learning Resource and Platform",
    "Paper_Link": "https://arxiv.org/pdf/2601.22987v1.pdf",
    "Tokenized": false,
    "Host": "GitHub",
    "Access": "Free",
    "Cost": "",
    "Test_Split": false,
    "Tasks": [
        "other"
    ],
    "Venue_Title": "",
    "Venue_Type": "",
    "Venue_Name": "",
    "Authors": [
        "Salem Lahlou"
    ],
    "Affiliations": [
        "Mohamed Bin Zayed University of Artificial Intelligence"
    ],
    "Abstract": "We present ArabicDialectHub, a cross-dialectal learning resource comprising a curated collection of 552 phrases across six Arabic varieties: Moroccan Darija, Lebanese, Syrian, Emirati, Saudi, and MSA. Generated using LLMs and validated by five native speakers, the collection is stratified by difficulty and organized thematically. The open-source platform provides translation exploration, adaptive quizzing with algorithmic distractor generation, cloud-synchronized progress tracking, and cultural context cards. Our contributions address gaps in pedagogical structuring and dialectal learning focus, providing a fully functional interactive system released under MIT license.",
    "Subsets": [],
    "Dialect": "mixed",
    "Language": "ar",
    "Script": "Arab",
    "Added_By": "qwen/qwen3.6-35b-a3b"
}