<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1111">
  <Title>Prototype-Driven Grammar Induction</Title>
  <Section position="2" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> We investigate prototype-driven learning for primarily unsupervised grammar induction. Prior knowledge is specified declaratively, by providing a few canonical examples of each target phrase type.</Paragraph>
    <Paragraph position="1"> This sparse prototype information is then propagated across a corpus using distributional similarity features, which augment an otherwise standard PCFG model. We show that distributional features areeffectiveatdistinguishingbracketlabels, butnot determiningbracketlocations. Toimprovethequality of the induced trees, we combine our PCFG induction with the CCM model of Klein and Manning (2002), which has complementary stengths: it identifies brackets but does not label them. Using only a handful of prototypes, we show substantial improvements over naive PCFG induction for English and Chinese grammar induction.</Paragraph>
  </Section>
class="xml-element"></Paper>