Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
This research was supported at SRI htternational by the Defense Advanced Reseat~ch Projects Agency under contract N00039-79-C-0118 ~¢ith the Naval Electronic Systems Commaw t The views and conchtsions contained in this document are those of the author and should not be interpreted as representative of the official policiex either expressed or bnplied, of the Defense Advanced Research Projects Agency, or the U. S. Goverttment. The author is gratefid to Barbara Grosz, Gary ttendrix and Terry Winograd for comments on an earlier draa of this paper. . | PROBLEM SOLVING APPLIED TO LANGUAGE GENERATION Douglas E. Appell Stanford University Stanford California SRI International Menlo Park California This research was supported al SRI International by the Defense Advanced Research Projects Agency under contract N00039-79-C-0118 with the Naval Electronic Systems Command. The views and conclusions contained in this document are those of the author and should not be interpreted as representative of the official policies either expressed or implied of the Defense Advanced Research Projects Agency or the u. s. Government. The author is grateful lo ữarbara Grosz Gary Hendrix and Terry Wmograd for comments on an earlier draft of this paper. I. Introduction Previous approaches to designing language understanding systems have considered language generation to be the activity of a highly specialized linguistic facility that is largely independent of other cognitive capabilities. All the requisite knowledge for generation is embodied in a generation module which with appropriate modifications to the lexicon is transportable between different domains and applications. Application programs construct messages in some internal representation such as first order predicate calculus or semantic networks and hand them to the generation module to be translated into natural language. The application program decides what to say the generation module decides how to say it. In contrast with dlls previous work this paper proposes an approach to designing a language generation system that builds on the view of language as action which has evolved from speech act theory see Austin 2 and Searle 11 . According to this view linguistic actions are actions planned to satisfy particular goals of the speaker similar to other actions like moving and looking language production is integrated with a speaker s problem solving processes. Illis approach is founded on the hypothesis that planning and performing linguistic actions is an activity that is not .
