<?xml version="1.0" standalone="yes"?>
<Paper uid="A00-2030">
  <Title>A Novel Use of Statistical Parsing to Extract Information from Text</Title>
  <Section position="12" start_page="232" end_page="232" type="concl">
    <SectionTitle>
11 Conclusions
</SectionTitle>
    <Paragraph position="0"> We have demonstrated, at least for one problem, that a lexicalized, probabilistic context-free parser with head rules (LPCFG-HR) can be used effectively for information extraction. A single model proved capable of performing all necessary sentential processing, both syntactic and semantic. We were able to use the Penn TREEBANK to estimate the syntactic parameters; no additional syntactic training was required. The semantic training corpus was produced by students according to a simple set of guidelines. This simple semantic annotation was the only source of task knowledge used to configure the model.</Paragraph>
  </Section>
class="xml-element"></Paper>