<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-2904">
  <Title>Improved Large Margin Dependency Parsing via Local Constraints and Laplacian Regularization</Title>
  <Section position="4" start_page="21" end_page="21" type="intro">
    <SectionTitle>
2 Lexicalized Dependency Parsing
</SectionTitle>
    <Paragraph position="0"> A dependency tree speci es which words in a sentence are directly related. That is, the dependency structure of a sentence is a directed tree where the nodes are the words in the sentence and links represent the direct dependency relationships between the words; see Figure 1. There has been a growing interest in dependency parsing in recent years.</Paragraph>
    <Paragraph position="1"> (Fox, 2002) found that the dependency structures of a pair of translated sentences have a greater degree of cohesion than phrase structures. (Cherry and Lin, 2003) exploited such cohesion between the dependency structures to improve the quality of word alignment of parallel sentences. Dependency relations have also been found to be useful in information extraction (Culotta and Sorensen, 2004; Yangarber et al., 2000).</Paragraph>
    <Paragraph position="2"> A key aspect of a dependency tree is that it does not necessarily report parts-of-speech or phrase labels. Not requiring parts-of-speech is especially bene cial for languages such as Chinese, where parts-of-speech are not as clearly de ned as English. In Chinese, clear indicators of a word's part-of-speech such as suf xes -ment , -ous or function words such as the , are largely absent. One of our motivating goals is to develop an approach to learning dependency parsers that is strictly lexical.</Paragraph>
    <Paragraph position="3"> Hence the parser can be trained with a treebank that only contains the dependency relationships, making annotation much easier.</Paragraph>
    <Paragraph position="4"> Of course, training a parser with bare word-to-word relationships presents a serious challenge due to data sparseness. It was found in (Bikel, 2004) that Collins' parser made use of bi-lexical statistics only 1.49% of the time. The parser has to compute back-off probability using parts-of-speech in vast majority of the cases. In fact, it was found in (Gildea, 2001) that the removal of bi-lexical statistics from a state of the art PCFG parser resulted in very little change in the output. (Klein and Manning, 2003) presented an unlexicalized parser that eliminated all lexicalized parameters. Its performance was close to the state of the art lexicalized parsers.</Paragraph>
    <Paragraph position="5"> Nevertheless, in this paper we follow the recent work of (Wang et al., 2005) and consider a completely lexicalized parser that uses no parts-of-speech or grammatical categories of any kind. Even though a part-of-speech lexicon has always been considered to be necessary in any natural language parser, (Wang et al., 2005) showed that distributional word similarities from a large unannotated corpus can be used to supplant part-of-speech smoothing with word similarity smoothing, to still achieve state of the art dependency parsing accuracy for Chinese.</Paragraph>
    <Paragraph position="6"> Before discussing our modi cations to large margin training for parsing in detail, we rst present the dependency parsing model we use. We then give a brief overview of large margin training, and then present our two modi cations. Subsequently, we present our experimental results on fully lexical dependency parsing for Chinese.</Paragraph>
  </Section>
class="xml-element"></Paper>