<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-2935">
  <Title>Language Independent Probabilistic Context-Free Parsing Bolstered by Machine Learning</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Unlexicalized probabilistic context-free parsing is a simple and flexible approach that nevertheless has shown good performance (Klein and Manning, 2003). We applied this approach to the shared task (Buchholz et al., 2006) for Arabic (HajiVc et al., 2004), Chinese (Chen et al., 2003), Czech (Bohmova et al., 2003), Danish (Kromann, 2003), Dutch (van der Beek et al., 2002), German (Brants et al., 2002), Japanese (Kawata and Bartels, 2000), Portuguese (Afonso et al., 2002), Slovene (Dzeroski et al., 2006), Spanish (Civit Torruella and Marti Antonin, 2002), Swedish (Nilsson et al., 2005), Turkish (Oflazer et al., 2003; Atalay et al., 2003), but not Bulgarian (Simov et al., 2005). In our approach we put special emphasis on language independence: We did not use any extraneous knowledge; we did not do any transformations on the treebanks; we restricted language-specific parameters to a small, easily manageable set (a classification of dependency relations into complements, adjuncts, and conjuncts/coordinators, and a switch for Japanese to include coarse POS tag information, see section 3.4). In a series of post-submission experiments, we investigated how much the parse results can help a machine learner.</Paragraph>
  </Section>
class="xml-element"></Paper>