@inproceedings{dekmak-etal-2026-dia2, title = "{DIA}2 - a Comprehensive and Diverse Diacritized {A}rabic Corpus for {NLP} Research", author = "Dekmak, Fatima and Elbassuoni, Shady and Shaban, Khaled and Hajj, Hazem and El-Hajj, Wassim and Abu Adla, Yasmine and Alabrash, Buthaina", editor = "Al-Khalifa, Hend and El-Haj, Mo and Ezzini, Saad", booktitle = "The 7th Workshop on Open-Source {A}rabic Corpora and Processing Tools ({OSACT}7) with 5 Shared Tasks", month = may, year = "2026", address = "Palma, Mallorca (Spain)", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.osact-1.14/", doi = "10.63317/3k2m7vtzunuk", pages = "115--130" }