@inproceedings{jarrar-hammouda-2024-qabas,
    title = "Qabas: An Open-Source {A}rabic Lexicographic Database",
    author = "Jarrar, Mustafa  and
      Hammouda, Tymaa Hasanain",
    editor = "Calzolari, Nicoletta  and
      Kan, Min-Yen  and
      Hoste, Veronique  and
      Lenci, Alessandro  and
      Sakti, Sakriani  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.lrec-main.1170/",
    pages = "13363--13370",
    abstract = "We present Qabas, a novel open-source Arabic lexicon designed for NLP applications. The novelty of Qabas lies in its synthesis of 110 lexicons. Specifically, Qabas lexical entries (lemmas) are assembled by linking lemmas from 110 lexicons. Furthermore, Qabas lemmas are also linked to 12 morphologically annotated corpora (about 2M tokens), making it the first Arabic lexicon to be linked to lexicons and corpora. Qabas was developed semi-automatically, utilizing a mapping framework and a web-based tool. Compared with other lexicons, Qabas stands as the most extensive Arabic lexicon, encompassing about 58K lemmas (45K nominal lemmas, 12.5K verbal lemmas, and 473 functional-word lemmas). Qabas is open-source and accessible online at https://sina.birzeit.edu/qabas"
}