A Reactive Approach to Explanation

Explanation is an interactive process, requiring a dialogue between advice-giver and advice-seeker. Yet current expert systems cannot participate in a dialogue with users. In particular these systems cannot clarify misunderstood explanations , elaborate on previous explanations, or respond to follow-up questions in the context of the ongoing dialogue. In this paper, we describe a reactive approach to explanation one that can participate in an ongoing dialogue and employs feedback from the user to guide subsequent explanations. Our system plans explanations from a rich set of explanation strategies, recording the system's discourse goals, the plans used to achieve them, and any assumptions made while planning a response. This record provides the dialogue context the system needs to respond appropriately to the user's feedback. We illustrate our approach with examples of disambiguating a follow-up question and producing a clarifying elaboration in response to a misunderstood explanation. 1 Introduction Explanation requires a dialogue. Users need to be able to ask follow-up questions if they do not understand an explanation or want further elaboration. Answers to such questions must take into account the dialogue context. Studies of advisory consultations between humans bear out this observation, showing that explanation is an interactive process between explainer and advice-seeker [Pollack et a/., 1982]. Studying student-teacher interactions, we found that advice-seekers frequently did not fully understand the instructor's response. They frequently asked follow-up questions requesting clarification , elaboration, or re-explanation. In some cases, follow-up questions took the form of a well-articulated query; in other cases, the follow-up was a vaguely articulated mumble or sentence fragment. Often the instruc-under a NASA Ames cooperative agreement number NCC 2-520. tor did not have much to go on, but still had to provide an appropriate response. Unfortunately, current expert systems cannot participate in a dialogue with users. In particular these systems cannot clarify misunderstood explanations, elaborate on previous explanations, or respond to follow-up questions in the context of the ongoing dialogue. In part, the explanation components of current expert systems are limited because they are quite simple. However, even the more sophisticated generation techniques employed in computational linguistics are inadequate for responding to follow-up questions. The problem is that both expert system explanation and natural language generation systems view generating responses as a one-shot process. That is, a system is assumed to have one opportunity to produce a response that the user will find satisfactory. This one-shot approach is clearly inconsistent with …