<?xml version="1.0" standalone="yes"?>
<Paper uid="W03-0611">
  <Title>Learning the Meaning and Usage of Time Phrases from a Parallel Text-Data Corpus</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2 Previous Research
</SectionTitle>
    <Paragraph position="0"> Linguists and lexicographers have used a number of different techniques to determine the meanings of words.</Paragraph>
    <Paragraph position="1"> These include asking native-speaker informants to judge the acceptability and oddness of test sentences (Cruse, 1986); defining word senses via lexicographic analysis of citations and corpora (Landau, 1984); and asking subjects to respond to 'fill in the blank' questions (Cassidy and Hall, 1996). These techniques have focused purely on texts, and have not analysed how texts and words relate to non-linguistic representations of the meanings of a text, which is our focus.</Paragraph>
    <Paragraph position="2"> Psychologists interested in categorisation have done formal experiments to determine which objects human subjects consider to be in a mental category (Rosch, 1978; Malt et al., 1999). If we assume that the meaning of a word is one or more mental categories, then this research has shed considerable light on what words mean.</Paragraph>
    <Paragraph position="3"> However, like all psychological research, it has examined language usage in an artificial experimental context, not naturally occurring language.</Paragraph>
    <Paragraph position="4"> In the NLP community, models of word meanings are typically either entered by a user or developer (for example in Microsoft's English Query natural-language interday hour wind dir wind speed  face) or derived from a hand-built knowledge base (eg, (Reiter, 1991)). There is growing interest in trying to learn word meanings from parallel text-data corpora, for example (Siskind, 2001; Barzilay and Lee, 2002; Roy, 2002). We believe our work is unusual because we are using naturally occurring texts and data. Siskind (2001), in contrast, used data which was explicitly created for his experiments; Barzilay and Lee (2002) used texts which subjects had written for a previous experiment; and Roy (2002) used both data and texts that were created for his experiments.</Paragraph>
  </Section>
class="xml-element"></Paper>