<?xml version="1.0" standalone="yes"?>
<Paper uid="W02-2016">
  <Title>Japanese Dependency Analysis using Cascaded Chunking</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Dependency analysis has been recognized as a basic process in Japanese sentence analysis, and a number of studies have been proposed. Japanese dependency structure is usually defined in terms of the relationship between phrasal units called bunsetsu segments (hereafter &amp;quot;segments&amp;quot;).</Paragraph>
    <Paragraph position="1"> Most of the previous statistical approaches for Japanese dependency analysis (Fujio and Matsumoto, 1998; Haruno et al., 1999; Uchimoto et al., 1999; Kanayama et al., 2000; Uchimoto et al., 2000; Kudo and Matsumoto, 2000) are based on a probabilistic model consisting of the following two steps. First, they estimate modification probabilities, in other words, how probable one segment tends to modify another. Second the optimal combination of dependencies is searched from the all candidates dependencies. Such a probabilistic model is not always efficient since it needs to calculate the probabilities for all possible dependencies and creates n.(n!1)=2 (where n is the number of segments in a sentence) training examples per sentence. In addition, the probabilistic model assumes that each pairs of dependency structure is independent.</Paragraph>
    <Paragraph position="2"> In this paper, we propose a new Japanese dependency parser which is more efficient and simpler than the probabilistic model, yet performs better in training and testing on the Kyoto University Corpus.</Paragraph>
    <Paragraph position="3"> The method parses a sentence deterministically only deciding whether the current segment modifies segment on its immediate right hand side. Moreover, it does not assume the independence constraint between dependencies</Paragraph>
  </Section>
class="xml-element"></Paper>