<?xml version="1.0" standalone="yes"?>
<Paper uid="C02-1048">
  <Title>Answering it with charts -- Dialogue in natural language and charts --</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Charts and graphics, as well as languages, are important modes of communication. Considering this importance, the automatic design of charts and graphics suitable for achieving a given communicative purpose has been studied actively (Maybury and Wahlster, 1998). It has been demonstrated that the characteristics of data drawn on the chart (Mackinlay, 1986), the intention to be achieved through the chart (Roth and Mattis, 1990), and the task accomplished using the chart (Casner, 1991) play important roles in designing appropriate charts. The automatic design of multimedia documents in which those charts coordinate with natural language text has also been studied (Roth et al., 1991; Kerpedjiev et al., 1998).</Paragraph>
    <Paragraph position="1"> In that research, systems take an assertion to be conveyed or a communicative goal to be achieved, and design the most appropriate multimedia presentation for that purpose. The purpose of drawing charts and graphics, however, is not restricted just to use in such presentations. In particular, as the drawing of quantitative charts helps to analyze huge amount of data and to find out its characteristics, they can be a useful means for interactive exploratory data analysis. An analyst, led by an interest or question, draws a chart, then a new interest or question comes up and she draws another chart.</Paragraph>
    <Paragraph position="2"> Through this process, the analyst finds out a characteristic behind the data or understands the reason for it.</Paragraph>
    <Paragraph position="3"> This paper discusses automatic quantitative chart design that supports such interactive exploratory data analysis. That is, a methodology is proposed for taking queries and requests expressed in natural language as input and answering them in charts through organizing that interaction into felicitous dialogue. The objectives of our research are an automatic chart design that considers dialogue context, and a dialogue mechanism that uses charts as its output mode.</Paragraph>
  </Section>
class="xml-element"></Paper>