<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-1054">
  <Title>Accurate Unlexicalized Parsing</Title>
  <Section position="10" start_page="0" end_page="0" type="concl">
    <SectionTitle>
10 Conclusion
</SectionTitle>
    <Paragraph position="0"> The advantages of unlexicalized grammars are clear enough - easy to estimate, easy to parse with, and time- and space-efficient. However, the dismal performance of basic unannotated unlexicalized grammars has generally rendered those advantages irrelevant. Here, we have shown that, surprisingly, the maximum-likelihood estimate of a compact unlexicalized PCFG can parse on par with early lexicalized parsers. We do not want to argue that lexical selection is not a worthwhile component of a state-of-the-art parser - certain attachments, at least, require it - though perhaps its necessity has been overstated.</Paragraph>
    <Paragraph position="1"> Rather, we have shown ways to improve parsing, some easier than lexicalization, and others of which are orthogonal to it, and could presumably be used to benefit lexicalized parsers as well.</Paragraph>
  </Section>
class="xml-element"></Paper>