@inproceedings{al-khalil-etal-2020-large,
    title = "A Large-Scale Leveled Readability Lexicon for {S}tandard {A}rabic",
    author = "Al Khalil, Muhamed  and
      Habash, Nizar  and
      Jiang, Zhengyang",
    editor = "Calzolari, Nicoletta  and
      B{\'e}chet, Fr{\'e}d{\'e}ric  and
      Blache, Philippe  and
      Choukri, Khalid  and
      Cieri, Christopher  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Isahara, Hitoshi  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, H{\'e}l{\`e}ne  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.lrec-1.373/",
    pages = "3053--3062",
    language = "eng",
    ISBN = "979-10-95546-34-4",
    abstract = "We present a large-scale 26,000-lemma leveled readability lexicon for Modern Standard Arabic. The lexicon was manually annotated in triplicate by language professionals from three regions in the Arab world. The annotations show a high degree of agreement; and major differences were limited to regional variations. Comparing lemma readability levels with their frequencies provided good insights in the benefits and pitfalls of frequency-based readability approaches. The lexicon will be publicly available."
}