<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-2928">
  <Title>Dependency Parsing with Reference to Slovene, Spanish and Swedish</Title>
  <Section position="4" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The system that we submitted for the CoNLL 2006 Shared Task, &amp;quot;Multingual Dependency Parsing,&amp;quot; (Buchholz et al., 2006) is a two stage pipeline. The first stage identifies unlabeled directed dependencies using an extension of the parser described in (Corston-Oliver et al., 2006). The second stage is a maximum entropy classifier that labels the directed dependencies. The system was trained on the twelve obligatory languages, as well as the optional language, Bulgarian (HajiVc et al., 2004; Simov et al., 2005; Simov and Osenova, 2003; Chen et al., 2003; B&amp;quot;ohmov'a et al., 2003; Kromann, 2003; van der Beek et al., 2002; Brants et al., 2002; Kawata and Bartels, 2000; Afonso et al., 2002; DVzeroski et al., 2006; Civit Torruella and Mart'i Anton'in, 2002; Nilsson et al., 2005; Oflazer et al., 2003; Atalay et al., 2003).</Paragraph>
    <Paragraph position="1"> Table 1 presents the results of the system described in the current paper on the CoNLL shared task, including the optional evaluation on Bulgarian. For Slovene, we ranked second with a labeled  dependency accuracy of 72.42%. This was not statistically significantly different from the top-ranked score of 73.44%. For Spanish, our labeled dependency accuracy of 80.36% is within 0.1% of the third-ranked score of 80.46%. Our unlabeled dependency accuracy for Swedish was the best of all the systems at 89.54%. Our labeled accuracy for Swedish, however, at 79.69%, fell far short of the third-best score of 82.31%. We therefore focus on Swedish when considering the impact of our choice of learning algorithm on our label accuracy.</Paragraph>
  </Section>
class="xml-element"></Paper>