<?xml version="1.0" standalone="yes"?>
<Paper uid="P99-1017">
  <Title>Using aggregation for selecting content when generating referring expressions</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> When generating referring expressions (RE), it is generally considered necessary to provide sufficient information so that the reader/hearer is able to identify the intended referent. A number of broadly related referring expression algorithms have been developed over the past decade based on the natural metaphor of 'ruling out distractors' (Reiter, 1990; Dale and Haddock, 1991; Dale, 1992; Dale and Reiter, 1995; Horacek, 1995). These special purpose algorithms constitute the 'standard' approach to determining content for RE-generation at this time; they have been developed solely for this purpose and have evolved to meet some specialized problems. In particular, it was found early on that the most ambitious RE goal-that of always providing the maximally concise referring expression necessary for the context ('full brevity')--is NP-haxd; subsequent work on RE-generation has therefore attempted to steer a course between computational tractability and coverage. One common feature of the favored algorithmic simplifications is their incrementality: potential descriptions are successively refined (usually non-destructively) to produce the final RE, which therefore may or may not be minimal. This is also often motivated on grounds of psychological plausibility.</Paragraph>
    <Paragraph position="1"> In this paper, we introduce a completely different metaphor for determining RE-content that may be considered in contrast to, or in combination with, previous approaches. The main difference lies in an orientation to the organization of a data set as a whole rather than to individual components as revealed during incremental search. Certain opportunities for concise expression that may otherwise be missed are then effectively isolated. The approach applies results from the previously unrelated generation task of 'aggregation', which is concerned with the grouping together of structurally related information.</Paragraph>
  </Section>
class="xml-element"></Paper>