Focus of Attention in Decision Support Systems

In this paper, we argue that natural language interfaces with discourse capabilities have an important role to play in decision support systems, because such interfaces are responsive to focus of attention in the mind of a human decision maker. The decision support systems that we will discuss employ graphical user interfaces. They are characterized by strict ordering requirements for commands, no reference to previous operations, and an often arbitrary, redundant, and repetitive order of operations. Natural language interfaces (NLIs) allow English language commands and questions to be input either via a keyboard or using a speech input device in a relatively natural and easy way, and discourse capabilities allow a user to input commands or questions that are connected in some specifiable ways. We will provide examples from systems that have been developed at the Army Research Laboratory (ARL) and at the Naval Research Laboratory (NRL). Currently these two laboratories are cooperating under the JDL Centers of Excellence in Artificial Intelligence Program in which NRL operates as a Center of Excellence for Natural Language Processing. We believe that research on natural language discourse will improve the capabilities of natural language interfaces to decision support systems as well as provide extensions that can ultimately make their graphical interfaces easier and more natural to use [Marsh 1991].