<?xml version="1.0" standalone="yes"?>
<Paper uid="N06-1020">
  <Title>Effective Self-Training for Parsing</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> We present a simple, but surprisingly effective, method of self-training a two-phase parser-reranker system using readily available unlabeled data. We show that this type of bootstrapping is possible for parsing when the bootstrapped parses are processed by a discriminative reranker.</Paragraph>
    <Paragraph position="1"> Our improved model achieves an f-score of 92.1%, an absolute 1.1% improvement (12% error reduction) over the previous best result for Wall Street Journal parsing.</Paragraph>
    <Paragraph position="2"> Finally, we provide some analysis to better understand the phenomenon.</Paragraph>
  </Section>
class="xml-element"></Paper>