“…Much recent research has been devoted to demonstrating how the quality of responses generated can be improved given a detailed model of the user -including what the user knows about the domain, how information should be presented to that user, and so forth (Appelt, 1985;McCoy, 1989;Paris, 1988;Kass and Finin, 1988). Moreover, if a system has only one opportunity to produce a text that achieves the speaker's goals without overor under-informing, boring or confusing the listener, then that system must have an enormous amount of detailed knowledge about the listener.…”