Building intelligent dialog systems
Susan McRoy, Syed Sumera Ali, Angelo Restifficar, Songsak Channarukul · intelligence · 1999
We overview our recent work in specifying and building intelligent dialog systems that collaborate with users for a task. As part of this work we have specified and built systems for: giving medical students an opportunity to practice their decision making skills in English (B2); performing template-based natural language generation (YAG); detecting and rebutting arguments (ARGUER); recognizing and repairing misunderstandings (RRM); and assessing and augmenting patients' health knowledge (PEAS). All of these systems make use of rich models of dialog for human-computer communication. Keywords: intelligent dialog systems, argumentation, natural language generation, misunderstanding, and repair 1 Introduction Computers have given people the power to process vast quantities of information, quickly and e#ectively. However, computers tend to respond to requests for information by presenting either too much information (such as a recommendation to buy a stock, accompanied by tables ...