@inproceedings{mekky-etal-2026-curriculum,
    title = "Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label {A}rabic Dialect Identification Models",
    author = "Mekky, Ali  and
      El Zeftawy, Mohamed  and
      Hassan, Lara  and
      Keleg, Amr  and
      Nakov, Preslav",
    booktitle = "Proceedings of the 13th Workshop on {NLP} for Similar Languages, Varieties and Dialects",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.vardial-1.22/",
    pages = "261--274",
    abstract = "Being modeled as a single-label classification task for a long time, recent work has argued that Arabic Dialect Identification (ADI) should be framed as a multi-label classification task. However, ADI remains constrained by the availability of single-label datasets, with no large-scale multi-label resources available for training. By analyzing models trained on single-label ADI data, we show that the main difficulty in repurposing such datasets for Multi-Label Arabic Dialect Identification (MLADI) lies in the selection of negative samples, as many sentences treated as negative could be acceptable in multiple dialects. To address these issues, we construct a multi-label dataset by generating automatic multi-label annotations using GPT-4o and binary dialect acceptability classifiers, with aggregation guided by the Arabic Level of Dialectness (ALDi). Afterward, we train a BERT-based multi-label classifier using curriculum learning strategies aligned with dialectal complexity and label cardinality. On the MLADI leaderboard, our best-performing LahjatBERT model achieves a macro F1 of 0.69, compared to 0.55 for the strongest previously reported system."
}