<?xml version="1.0" standalone="yes"?>
<Paper uid="C02-1127">
  <Title>Location Normalization for Information Extraction*</Title>
  <Section position="6" start_page="0" end_page="0" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> This paper presents a method of location normalization for information extraction with experimental results and its applications. In future work, we will integrate a expanded location gazetteer including names of landmarks, mountains and lakes such as Holland Tunnel (in New York, not in Holland) and Hoover Dam (in Arizona, not in Alabama), to enlarge the system coverage, and adjust the scoring weight given in Table 1 for better normalization results. Using context information other than location names can be a subtask for determining specific location names such as bridge or area names.</Paragraph>
  </Section>
class="xml-element"></Paper>