<?xml version="1.0" standalone="yes"?>
<Paper uid="X98-1011">
  <Title>EXTRACTING AND NORMALIZING TEMPORAL EXPRESSIONS</Title>
  <Section position="10" start_page="55" end_page="55" type="concl">
    <SectionTitle>
6. CONCLUSIONS AND FUTURE
WORK
</SectionTitle>
    <Paragraph position="0"> This paper has examined the task of extracting and normalizing temporal expressions, and has described the NLToolset's approach to accomplishing this task. It has also described the use of a learning program to deal with the complexity of developing such a system, as well as the methodology for normalizing temporal information for database use.</Paragraph>
    <Paragraph position="1"> As the time extraction process is exercised across applications, it will be expanded to cover more and more cases.</Paragraph>
    <Paragraph position="2"> Future research work may address the issue of ambiguous temporal expressions. Statistical means may be appropriate for representing the uncertainty of an interval representation. Comparisons across languages may also prove enlightening. In the near future, an existing prototype application will be translated into the Spanish language.</Paragraph>
  </Section>
class="xml-element"></Paper>