<?xml version="1.0" standalone="yes"?>
<Paper uid="W99-0905">
  <Title>Resolving Translation Ambiguity using Non-parallel Bilingual Corpora</Title>
  <Section position="3" start_page="0" end_page="31" type="intro">
    <SectionTitle>
2 Overview of the method
</SectionTitle>
    <Paragraph position="0"> Figure 1 shows an overview of the entire method.</Paragraph>
    <Paragraph position="1"> Components inside the dotted line on the left represent word-sense disambiguation (WSD) in the source language. There are two sub-processes: distributional clustering and categorizing. The former automatically identifies different usages (or senses) of the given source word (shown at top center) in the  source language corpus and creates a profile, referred to as the &amp;quot;sense profile&amp;quot; for each class. The categorization process chooses the profile most relevant to the input word whose sense is implicitly given by its surrounding context.</Paragraph>
    <Paragraph position="2"> Located to the right is what we call the sense..</Paragraph>
    <Paragraph position="3"> translation linking process. It is responsible for as-sociating each semantic profile with the most likely translation of the source word (for which the seman-. tic profile is derived). The result of this process is registered in the sense-$ranslation table.</Paragraph>
    <Paragraph position="4"> The table look-up process, bottom center, simply retrieves the translation associated with the sense identified by the categorization process.</Paragraph>
  </Section>
class="xml-element"></Paper>