A NATURAL-LANGUAGE PROCESSING BASED GROUP DECISION-SUPPORT SYSTEM

Group Decision Support Systems (GDSSs) are currently used primarily as surface-level discussion tools. That is, current GDSSs do not allow g roup members to easily access information in deeper levels, such as th e data base, model base, and application programs. This paper describe s ways in which GDSSs can be improved by using a natural language inte rface to allow group members to communicate with deeper-level informat ion systems using human languages. The system consists of database, mo del base, application programs and natural language interface system. The system is designed to both route questions to appropriate subsyste ms and translate these questions into the computer language controllin g these subsystems. Finally, experimental results demonstrate the feas ibility of the technique.