<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-2131">
  <Title>Finding Structural Correspondences from Bilingual Parsed Corpus for Corpus-b sed Translation</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> So far, a number of methodologies and systelns for machine trauslation using large corpora exist.</Paragraph>
    <Paragraph position="1"> They include example-based at)proaches \[7, 8, 9, 12\], pattern-based approaches \[10, 11, 14\], and statistical approaches. For instance, example-based approaches use a large set of translation patterns each of which is a pair of parsed structures of a source-language fragment and its target-language translation fragment. Figure 1 shows an exanlple of translation by an example-based method, ill which translation patterns (pl) and (p2) are selected as similar to a (left hand) Japanese dependency structure, and an (right hand) English dependency structure is constructed by merging the target parts of these translation patterns 1.</Paragraph>
    <Paragraph position="2"> In this kind of system, it is very important to collect a large set of translatiou patterns easily and efficiently. Previous systems, however, collect such translation patterns mostly manually. Therefore, they have problems in terms of the development cost.</Paragraph>
    <Paragraph position="3"> 1Words in parenthesis at the nodes of the Japanese dependency structure are representative English translations, and are for explanation.</Paragraph>
    <Paragraph position="4"> This paper tries to provide solutions for this issue by proposing methods for finding structural correspondences of parsed trees of a translation pair. These structural correspondences are used as bases of translation patterns in corpus-based approaches. null Figure 2 shows an example of extracting structural correspondences. In this figure, tile left tree is a Japanese dependency tree, the right tree is a dependency tree of its English translation, dotted arrows represent word correspondence, and a pair of boxes connected by a solid line represent phrasal correspondence. We would like to extract these  word and phrasal correspondeuces automatically.</Paragraph>
    <Paragraph position="5"> In what follows, we will describe details of procedures for finding these structural correspondences.</Paragraph>
  </Section>
class="xml-element"></Paper>