@inproceedings{sellami-etal-2012-exploiting,
    title = "Exploiting {W}ikipedia as a Knowledge Base for the Extraction of Linguistic Resources: Application on {A}rabic-{F}rench Comparable Corpora and Bilingual Lexicons",
    author = "Sellami, Rahma  and
      Sadat, Fatiha  and
      Hadrich Belguith, Lamia",
    editor = "Farghaly, Ali  and
      Oroumchian, Farhad",
    booktitle = "Fourth Workshop on Computational Approaches to Arabic-Script-based Languages",
    month = nov # " 1",
    year = "2012",
    address = "San Diego, California, USA",
    publisher = "Association for Machine Translation in the Americas",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2012.amta-caas14.10/",
    pages = "72--79",
    abstract = "We present simple and effective methods for extracting comparable corpora and bilingual lexicons from Wikipedia. We shall exploit the large scale and the structure of Wikipedia articles to extract two resources that will be very useful for natural language applications. We build a comparable corpus from Wikipedia using categories as topic restrictions and we extract bilingual lexicons from inter-language links aligned with statistical method or a combined statistical and linguistic method."
}