Generating explanations in context

Abstract
If user interfaces are to reap the benefits of natural language interaction, they must be endowed withthe properties that make human natural language interaction so effective. Human-human explanationis an inherently incremental and interactive process. New information must be highlighted and relatedto what has already been presented. In this paper, we describe the explanation component of a medicalinformation-giving system. We describe the architectural features that enable this component...

This publication has 0 references indexed in Scilit: