<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-2932">
  <Title>Multilingual Dependency Analysis with a Two-Stage Discriminative Parser</Title>
  <Section position="3" start_page="0" end_page="216" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Often in language processing we require a deep syntactic representation of a sentence in order to assist further processing. With the availability of resources such as the Penn WSJ Treebank, much of the focus in the parsing community had been on producing syntactic representations based on phrase-structure.</Paragraph>
    <Paragraph position="1"> However, recently their has been a revived interest in parsing models that produce dependency graph representations of sentences, which model words and their arguments through directed edges (Hudson, 1984; MelprimeVcuk, 1988). This interest has generally come about due to the computationally efficient and flexible nature of dependency graphs and their ability to easily model non-projectivity in freer-word order languages. Nivre (2005) gives an introduction to dependency representations of sentences and recent developments in dependency parsing strategies.</Paragraph>
    <Paragraph position="2"> Dependency graphs also encode much of the deep syntactic information needed for further processing. This has been shown through their successful use in many standard natural language processing tasks, including machine translation (Ding and Palmer, 2005), sentence compression (McDonald, 2006), and textual inference (Haghighi et al., 2005).</Paragraph>
    <Paragraph position="3"> In this paper we describe a two-stage discriminative parsing approach consisting of an unlabeled parser and a subsequent edge labeler. We evaluate this parser on a diverse set of 13 languages using data provided by the CoNLL-X shared-task organizers (Buchholz et al., 2006; 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). The results are promising and show the language independence of our system under the assumption of a labeled dependency corpus in the target language.</Paragraph>
    <Paragraph position="4"> For the remainder of this paper, we denote by x = x1,...xn a sentence with n words and by y a corresponding dependency graph. A dependency graph is represented by a set of ordered pairs (i,j) [?] y in which xj is a dependent and xi is the corresponding head. Each edge can be assigned a label l(i,j) from a finite set L of predefined labels. We  assume that all dependency graphs are trees but may be non-projective, both of which are true in the data sets we use.</Paragraph>
  </Section>
class="xml-element"></Paper>