<?xml version="1.0" standalone="yes"?>
<Paper uid="W99-0623">
  <Title>Exploiting Diversity in Natural Language Processing: Combining Parsers</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The natural language processing community is in the strong position of having many available approaches to solving some of its most fundamental problems.</Paragraph>
    <Paragraph position="1"> The machine learning community has been in a similar situation and has studied the combination of multiple classifiers (Wolpert, 1992; Heath et al., 1996).</Paragraph>
    <Paragraph position="2"> Their theoretical I finding is simply stated: classification error rate decreases toward the noise rate exponentially in the number of independent, accurate classifiers. The theory has also been validated empirically. null Recently, combination techniques have been investigated for part of speech tagging with positive results (van Halteren et al., 1998; Brill and Wu, 1998). In both cases the investigators were able to achieve significant improvements over the previous best tagging results. Similar advances have been made in machine translation (Frederking and Nirenburg, 1994), speech recognition (Fiscus, 1997) and named entity recognition (Borthwick et al., 1998).</Paragraph>
    <Paragraph position="3"> The corpus-based statistical parsing community has many fast and accurate automated parsing systems, including systems produced by Collins (1997), Charniak (1997) and Ratnaparkhi (1997). These three parsers have given the best reported parsing results on the Penn Treebank Wall Street Journal corpus (Marcus et al., 1993). We used these three parsers to explore parser combination techniques.</Paragraph>
  </Section>
class="xml-element"></Paper>