Ifuser interfaces are toreap thebenefit sofnatural language interaction, they must reendowed with the properties that makehumannatural language interaction so effective. Human-human explanation is an inherently incremental and interactive process. Newinformationmust behighlighted and related to what has already been presented. In this paper, we describe the explanation component of a medical information-giving syst em. We describe the architectural features that enable this component to generate subsequent explanations that take into account the context created by its prior utterances.
No takes yet. Share an insight, caveat, or question.
Carenini et al. (1993) studied this question.