@inproceedings{keskes-etal-2012-clause,
    title = "Clause-based Discourse Segmentation of {A}rabic Texts",
    author = "Keskes, Iskandar  and
      Benamara, Farah  and
      Belguith, Lamia Hadrich",
    editor = "Calzolari, Nicoletta  and
      Choukri, Khalid  and
      Declerck, Thierry  and
      Do{\u{g}}an, Mehmet U{\u{g}}ur  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
    month = may,
    year = "2012",
    address = "Istanbul, Turkey",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/ingest-emnlp/L12-1559/",
    pages = "2826--2832",
    abstract = "This paper describes a rule-based approach to segment Arabic texts into clauses. Our method relies on an extensive analysis of a large set of lexical cues as well as punctuation marks. Our analysis was carried out on two different corpus genres: news articles and elementary school textbooks. We propose a three steps segmentation algorithm: first by using only punctuation marks, then by relying only on lexical cues and finally by using both typology and lexical cues. The results were compared with manual segmentations elaborated by experts."
}