@inproceedings{halpern-2008-exploiting,
    title = "Exploiting Lexical Resources for Disambiguating {CJK} and {A}rabic Orthographic Variants",
    author = "Halpern, Jack",
    editor = "Calzolari, Nicoletta  and
      Choukri, Khalid  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Odijk, Jan  and
      Piperidis, Stelios  and
      Tapias, Daniel",
    booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
    month = may,
    year = "2008",
    address = "Marrakech, Morocco",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/fix-sig-urls/L08-1319/",
    abstract = "The orthographical complexities of Chinese, Japanese, Korean (CJK) and Arabic pose a special challenge to developers of NLP applications. These difficulties are exacerbated by the lack of a standardized orthography in these languages, especially the highly irregular Japanese orthography and the ambiguities of the Arabic script. This paper focuses on CJK and Arabic orthographic variation and provides a brief analysis of the linguistic issues. The basic premise is that statistical methods by themselves are inadequate, and that linguistic knowledge supported by large-scale lexical databases should play a central role in achieving high accuracy in disambiguating and normalizing orthographic variants."
}