<?xml version="1.0" standalone="yes"?>
<Paper uid="W03-0428">
  <Title>Named Entity Recognition with Character-Level Models</Title>
  <Section position="2" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> We discuss two named-entity recognition models which use characters and character a4 -grams either exclusively or as an important part of their data representation. The first model is a character-level HMM with minimal context information, and the second model is a maximum-entropy conditional markov model with substantially richer context features. Our best model achieves an overall Fa5 of 86.07% on the English test data (92.31% on the development data). This number represents a 25% error reduction over the same model without word-internal (substring) features.</Paragraph>
  </Section>
class="xml-element"></Paper>