@inproceedings{alahmari-2025-sadslyc,
    title = "{SADSL}y{C}: A Corpus for Saudi {A}rabian Multi-dialect Identification through Song Lyrics",
    author = "Alahmari, Salwa Saad",
    editor = "Ezzini, Saad  and
      Alami, Hamza  and
      Berrada, Ismail  and
      Benlahbib, Abdessamad  and
      El Mahdaouy, Abdelkader  and
      Lamsiyah, Salima  and
      Derrouz, Hatim  and
      Haddad Haddad, Amal  and
      Jarrar, Mustafa  and
      El-Haj, Mo  and
      Mitkov, Ruslan  and
      Rayson, Paul",
    booktitle = "Proceedings of the 4th Workshop on Arabic Corpus Linguistics (WACL-4)",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2025.wacl-1.4/",
    pages = "38--43",
    abstract = "This paper presents the Saudi Arabian Dialects Song Lyrics Corpus (SADSLyC), the first dataset featuring song lyrics from the five major Saudi dialects: Najdi (Central Region), Hijazi (Western Region), Shamali (Northern Region), Janoubi (Southern Region), and Shargawi (Eastern Region). The dataset consists of 31,358 sentences, with each sentence representing a self-contained verse in a song, totaling 151,841 words. Additionally, we present a baseline experiment using the SaudiBERT model to classify the fine-grained dialects in the SADSLyC Corpus. The model achieved an overall accuracy of 73{\%} on the test dataset."
}