<?xml version="1.0" standalone="yes"?>
<Paper uid="P01-1009">
  <Title>Alternative Phrases and Natural Language Information Retrieval</Title>
  <Section position="7" start_page="8" end_page="8" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> In this paper, I brie y presented a formal analysis for a large class of words called alternative markers. The analysis elegantly captures the desired phenomena by separating assertion and presupposition and making use of alternative phrases and the \use existing objects&amp;quot; heuristic.</Paragraph>
    <Paragraph position="1"> A simple pattern matching approach would fail to capture examples requiring knowledge and those with anaphora. Furthermore, sophisticated noun phrase detection would be required for many examples. null I then show that alternative phrases appear frequently enough in dialog to warrant serious attention, yet present natural language search engines perform poorly on queries containing alternative phrases. However, by approximating my semantic analysis into a form understood by a natural language search engine, I showed that the performance of that search engine improved dramatically. As the operational semantics of natural language applications improves, even larger improvements are possible.</Paragraph>
    <Paragraph position="2"> Further improvement is also possible by approaching the problem from the other direction.</Paragraph>
    <Paragraph position="3"> Alternative phrases can be used to help characterize documents beyond the simple word indices used in many current systems. This richer data can be used in the retrieval process to more e ectively identify appropriate documents.</Paragraph>
  </Section>
class="xml-element"></Paper>