<?xml version="1.0" standalone="yes"?>
<Paper uid="C02-1130">
  <Title>Fine Grained Classification of Named Entities</Title>
  <Section position="7" start_page="3" end_page="3" type="relat">
    <SectionTitle>
6. Related Work
</SectionTitle>
    <Paragraph position="0"> While much research has gone into the coarse categorization of named entities, we are not aware of much previous work using learning algorithms to perform more fine-grained classification.</Paragraph>
    <Paragraph position="1"> Wacholder et al. (1997) use hand-written rules and knowledge bases to classify proper names into broad categories. They employ an aggregation method similar to MemRun, but do not use multiple thresholds to increase accuracy.</Paragraph>
    <Paragraph position="2"> MacDonald (1993) also uses hand-written rules for coarse named entity categorization. However, where Wacholder et al. use evidence internal to the entity name, MacDonald employs local context to aid in classification. Such hand-written heuristic rules resemble those we automatically generate.</Paragraph>
    <Paragraph position="3"> Bechet et al. (2000) use a decision tree algorithm to classify unknown proper names into the categories: first name, last name, country, town, and organization. This is still a much coarser distinction than that focused on in this research.</Paragraph>
    <Paragraph position="4"> Further, Bechet et al. focused only on those proper names embedded in complex noun phrases (NPs), using only elements in the NP as its feature set.</Paragraph>
  </Section>
class="xml-element"></Paper>