• DocumentCode
    2953167
  • Title

    A hybrid knowledge representation model in a natural language interface to MS-DOS

  • Author

    Michos, S.E. ; Magoulas, G.D. ; Fakotakis, N.

  • Author_Institution
    Dept. of Electr. & Comput. Eng., Patras Univ., Greece
  • fYear
    1995
  • fDate
    5-8 Nov 1995
  • Firstpage
    480
  • Lastpage
    483
  • Abstract
    A hybrid model for representing knowledge in a Greek natural language interface to MS-DOS is presented. This model employs semantic knowledge of the operating system domain to develop a hybrid architecture integrating symbolic and connectionist modules for recognizing the MS-DOS command labels of related or unrelated successive natural language user messages. This approach was deeply motivated by handling ellipsis, ambiguity and flexibility of sentence structure as well as possible. A comparative experimental evaluation of this approach to a symbolic one illustrating their pros and cons is also given. Finally, ways of extending this model are proposed with the view of making the natural language interface more user friendly and functional
  • Keywords
    knowledge representation; natural language interfaces; neural net architecture; operating systems (computers); symbol manipulation; Greek natural language interface; MS-DOS command label recognition; ambiguity; connectionist module; ellipsis; flexibility; functionality; hybrid architecture; hybrid knowledge representation model; natural language user messages; operating system domain; semantic knowledge; sentence structure; symbolic module; user friendliness; Artificial intelligence; Communication system control; Computer architecture; Control systems; Knowledge representation; Laboratories; Natural languages; Telecommunication computing; Telecommunication control; Wire;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Tools with Artificial Intelligence, 1995. Proceedings., Seventh International Conference on
  • Conference_Location
    Herndon, VA
  • ISSN
    1082-3409
  • Print_ISBN
    0-8186-7312-5
  • Type

    conf

  • DOI
    10.1109/TAI.1995.479844
  • Filename
    479844