Generating customized text and graphics in the COMET explanation testbed

It is shown 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 same concepts, and thus better meets the needs of different users. The authors focus on four ways in which COMET produces different explanations for the same concepts, describing how it is influenced by the plan containing the concept, by user background knowledge, by previous dialogue, and by interactive exploration of an explanation