Generating customized text and graphics in the COMET explanation testbed Conference Paper uri icon


  • ABSTRACT For many applications that must explain reasoning, processes, or plans to their users, multimedia explanations are more effective than text or pictures alone the use of two or more modalities makes it possible to communicate the same or complementary itiormation in different ways. While hypermedia is a currently available technology for providing such explanations, conventional implementations do not adequately address the needs of different users. In this paper, we show how COMET, a system that uses natural language and graphics generation components to produce the text and pictures of its explanations dynamically, can create a variety of different explanations to explain the s: lme concepts, and thus better meets the needs of ditlerent users. We focus on four ways in which COMET produces dit% erent explanations for the same concepts, describing how it is …

publication date

  • January 1, 1991