<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1411">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics Group-based Generation of Referring Expressions</Title>
  <Section position="3" start_page="0" end_page="73" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> In the last two decades, many researchers have studied the generation of referring expressions to enable computers to communicate with humans about objects in the world.</Paragraph>
    <Paragraph position="1"> In order to refer to an intended object (the target) among others (distractors), most past work (Appelt, 1985; Dale and Haddock, 1991; Dale, 1992; Dale and Reiter, 1995; Heeman and Hirst, 1995; Horacek, 1997; Krahmer and Theune, 2002; van Deemter, 2002; Krahmer et al., 2003) utilized attributes of the target and binary relations between the target and distractors. Therefore, these methods cannot generate proper referring expressions in situations where there is no significant surface difference between the target and distractors, and no binary relation is useful to distinguish the target. Here, a proper referring expression [?] Currently at Honda Research Institute Japan Co., Ltd. + Currently at Hitachi, Ltd.</Paragraph>
    <Paragraph position="2"> means a concise and natural linguistic expression enabling hearers to identify the target.</Paragraph>
    <Paragraph position="3"> Forexample, consider indicating object b to per-son P in the situation of Figure 1. Note that labels a, b and c are assigned for explanation to the readers, and person P does not share these labels with the speaker. Because object b is not distinguishable from objects a or c by means of their appearance, one would try to use a binary relation between object b and the table, i.e., &amp;quot;a ball to the right of the table&amp;quot;. However, &amp;quot;to the right of&amp;quot; is not a discriminatory relation, for objects a and c are also located to the right of the table. Using a and c as a reference object instead of the table does not make sense, since a and c cannot be uniquely identified because of the same reason that b cannot be identified. Such situations have drawn less attention (Stone, 2000), but can frequently occur in some domains such as object arrangement (Tanaka et al., 2004).</Paragraph>
    <Paragraph position="4">  Inthe situation ofFigure 1, the speaker can indicate object b to person P with a simple expression &amp;quot;the front ball&amp;quot;. In order to generate such an expression, one must be able to recognize the salient perceptual group of the objects and use the n-ary relative relations in the group.</Paragraph>
    <Paragraph position="5">  To overcome the problem described above, Funakoshi et al. (2004) proposed a method of generating Japanese referring expressions that utilizes n-ary relations among members of a group. They, however, dealt with the limited situations where only homogeneous objects are randomly arranged (see Figure 2). Thus, their method could handle only spatial n-ary relation, and could not handle attributes and binary relations between objects which have been the main concern of the past research. null In this paper, we extend the generation method proposed by (Funakoshi et al., 2004) so as to handle object attributes and binary relations between objects as well. In what follows, Section 2 shows an extension of the SOG representation that was proposed in (Funakoshi et al., 2004). Our new method will be described in Section 3 and evaluated in Section 4. Finally we conclude the paper in Section 5.</Paragraph>
  </Section>
class="xml-element"></Paper>