• DocumentCode
    2118034
  • Title

    Deep domain models for discourse analysis

  • Author

    Joskowicz, Leo ; Ksiezyck, T. ; Grishman, Ralph

  • Author_Institution
    Dept. of Comput. Sci., New York Univ., NY, USA
  • fYear
    1989
  • fDate
    27-31 Mar 1989
  • Firstpage
    195
  • Lastpage
    200
  • Abstract
    The authors address the problem of discourse analysis, and in particular finding causal relations between facts mentioned in messages, using a detailed domain model. This work is part of the PROTEUS (Prototype Text Understanding System) project, whose objective is to understand short narrative message about equipment installed in Navy ships. Casualty reports (CASREPs) describe failures of this equipment, together with maintenance actions performed by the crew onboard. To capture the domain knowledge, the authors built a model of the equipment installed on the ship (initially, the starting air system) and demonstrated is use in several aspects of language understanding. The PROTEUS system has been substantially implemented and debugged and has been publically demonstrated operating on a small set of actual CASREPs
  • Keywords
    knowledge acquisition; maintenance engineering; natural languages; naval engineering; CASREPs; Navy ships; PROTEUS; Prototype Text Understanding System; casualty reports; causal relations; discourse analysis; domain knowledge; language understanding; maintenance actions; narrative message; starting air system; Computational modeling; Computer science; Computer simulation; Equipment failure; Marine vehicles; Mathematical model; Natural language processing; Natural languages; Prototypes; Robustness;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    AI Systems in Government Conference, 1989.,Proceedings of the Annual
  • Conference_Location
    Washington, DC
  • Print_ISBN
    0-8186-1934-1
  • Type

    conf

  • DOI
    10.1109/AISIG.1989.47325
  • Filename
    47325