<?xml version="1.0" standalone="yes"?>
<Paper uid="J88-3006">
  <Title>TAILORING OBJECT DESCRIPTIONS TO A USER'S LEVEL OF EXPERTISE</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
64 Computational Linguistics, Volume 14, Number 3, September 1988
</SectionTitle>
    <Paragraph position="0"> C~ile L. Paris Tailoring Object Descriptions to a User's Level of Expertise domain knowledge affected only the amount of detail provided in the text (Wallis and Shortliffe 1982).</Paragraph>
    <Paragraph position="1"> In this work, we show how the two discourse strategies found in texts can be used to provide answers to users whose domain knowledge falls anywhere along a knowledge spectrum, from naive to expert. We have implemented them in TAILOR, a computer system that generates descriptions of physical objects.</Paragraph>
    <Paragraph position="2"> TAILOR uses one of the two discourse strategies identified in texts to construct a description for either a novice or an expert. It can merge the strategies automatically in a systematic way to produce a wide variety of different descriptions for users who fall between the extremes of novice and expert. This means TAILOR is able to generate descriptions to a whole range of users, rather that just for an a priori set of user stereotypes.</Paragraph>
  </Section>
class="xml-element"></Paper>