<?xml version="1.0" standalone="yes"?>
<Paper uid="P86-1016">
  <Title>The ROMPER System: Responding to Object-Related Misconceptions using Perspective 1</Title>
  <Section position="2" start_page="0" end_page="97" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> A study of transcripts of expert-user dialogues reveals that users often exhibit misconceptions about the objects modeled in a domain. This paper describes the ROMPER system (Responding to Object-Related Misconceptions using PERspective) which is able to respond to certain classes of these misconceptions in a principled manner. In doing so the system sheds light not only on the process of correcting misconceptions, but also on issues in natural-language generation, user models, and modeling certain contextual effects by a &amp;quot;filtering&amp;quot; of the knowledge representation.</Paragraph>
    <Paragraph position="1"> The ROMPER system functions as a part of a natural-language interface to a database or expert system. Input to ROMPER is a specification that a misconception has been detected. In this work a miscwnception is defined to be some discrepancy between what the system believes (i.e., what is contained in the system knowledge base) and what the user believes (as exhibited through the conversation). The system knowledge base includes an object taxonomy and knowledge about object attributes and their possible values.</Paragraph>
    <Paragraph position="2"> Several factors may influence the structure and content of responses to queries that reveal misconceptions. These indude the goals of the conversstional participants. If the misconception is not important to these goals, the response may not address the misconception or may address it only minimaliy. ROMPER is concerned with correcting misconceptions that are important to the current goals of the conversational participants and is thus concerned with generating a maximal IMuch of this work wu done while the author wM at the University of Pennsylvania and was partially supported by the ARO grant DAA20-84-K-0061 and the NFS grant MCS81-07290.</Paragraph>
    <Paragraph position="3"> response. This response is aimed at eliminating the discrepancy between what the user believes and what the system believes by bringing the user's knowledge into line with the system's.</Paragraph>
    <Paragraph position="4"> This means that the system must not only give the user the correct information, but must present it in such a way so as to have the user adopt that information. ROMPER has a user model available to aid in this task. The user model constitutes what the system believes the user believes about the domain. It contains the same kind of information as is contained in the system's knowledge base -- an object taxonomy and information about objects' attributes and their values. The content of the user model, however, may be very different from the content of the system's knowledge base. For instance, it may contain less information than is contained in the system knowledge base, or it may contain some information that is inconsistent with the system knowledge base. The user model will not, however, contain more information than is contained in the system knowledge base since the system is assumed to be an expert in the domain.</Paragraph>
    <Paragraph position="5"> In an attempt to respond to a misconception in a natural way, the system operates on the model of the user attempting to find certain structural configurations which might indicate support for the misconception. If one of the configurations is found, then a response is generated that refutes the found support. ROMPER is specifically concerned with responding to two kinds of misconceptions: those involving an object's classification (which I call misclassifications) and those involving an objects attributes (which I call n~attributlons). Certain structural configurations have been identified indicating possible support for both kinds of misconceptions. Each identified configuration has a response strategy associated with it which may be instantiated to respond to the misconception.</Paragraph>
    <Paragraph position="6"> The whole process is made context sensitive by a new notion of object perspective which acts to filter the user model, highlighting those aspects which are made important by previous dialogue, while suppressing others. The filtering gained by object perspective allows the same misconception by the same user to be responded to differently in different contextual situations.</Paragraph>
    <Paragraph position="7"> Output from ROMPER is a formal specification of a response. This specification is then input to the MUMBLE system \[McDS01 which, using a dictionary and grammer supplied by Robin Karlin \[Kar85\], produces actual English text.</Paragraph>
  </Section>
class="xml-element"></Paper>