<?xml version="1.0" standalone="yes"?>
<Paper uid="C02-1048">
  <Title>Answering it with charts -- Dialogue in natural language and charts --</Title>
  <Section position="5" start_page="0" end_page="0" type="concl">
    <SectionTitle>
5 Discussion
</SectionTitle>
    <Paragraph position="0"> Appropriateness of charts is known to be a function of several factors. This paper revealed that discourse context is one of those factors in addition to those already known such as characteristic of data and user intentions, and proposed a methodology for addressing that factor properly. To our knowledge, there are few studies on automatic chart design for such interactive situations as discussed here. There are many studies on interactive graph drawing of course (Roth et al., 1994). Those, however, are concerned with tools for producing a graph interactively that achieves the user's intention. Their standpoint differs from ours, and the mode used for their interactions is direct manipulation not natural language.</Paragraph>
    <Paragraph position="1"> Our proposal partially overlaps with recent studies on automatic chart design. Our logical form has a lot in common with the content language in (Green et al., 1998). The objective of their research, however, is to describe communicative goals to be achieved through generating graphics and text, and differs from ours, which is to describe the user's requests in order to respond to them using charts.</Paragraph>
    <Paragraph position="2"> Our perspective plays a similar role to that of intention in PostGraphe (Fasciano and Lapalme, 1996).</Paragraph>
    <Paragraph position="3"> However, there is a crucial difference in that, while their intention is given as input, our perspective is acquired from the user's utterances, data characteristics and dialogue context.</Paragraph>
    <Paragraph position="4"> Most of the framework proposed in this paper has been implemented. The prototype system accepts such a wide range of Japanese expressions that the appropriateness of our proposal can be confirmed, though the understanding of those expressions is driven by a simple pattern-based mechanism. The matter worth special mention is the prototype's chart redraw mechanism. As suggested in this paper, a correct chart in a certain context is one that can be realized by minimum change to the chart as the context, and loses minimum information from it. We supposed that changes and loss of information mattered because considerable mental loads are needed to relate new information in the new chart to old information in the context. In order to reduce those loads, we made the process of change visually understandable. Specifically, the system shows animations that represent which component of the current chart moves and changes to which component of the new one. This feature has received a favorable reception in demonstrations.</Paragraph>
    <Paragraph position="5"> A lot remains for future work. First, we will consider answering wh- and yes-no interrogatives in charts in addition to answering requests to show charts. Answering such questions fluently requires collaboration between charts and text. Then, we will examine richer chart realization. We should consider not only increasing the kinds of chart form covered, but also assembling more than one chart to achieve a certain goal. In addition, dimensions such as visual prompts should be incorporated. Lastly, in the context of information visualization, the effects of animation introduced in the implementation of the prototype should be measured quantitatively to prove that it really can reduce mental load rather than merely make itself conspicuous.</Paragraph>
  </Section>
class="xml-element"></Paper>