<?xml version="1.0" standalone="yes"?>
<Paper uid="N03-1015">
  <Title>Word Sense Acquisition from Bilingual Comparable Corpora</Title>
  <Section position="8" start_page="2" end_page="2" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> We presented a translingual distributional word clustering method enabling word senses, exactly a hierarchy of clusters of translation equivalents, to be acquired from a comparable corpus and a bilingual dictionary. Its effectiveness was demonstrated through an experiment using Wall Street Journal and Nihon Keizai Shimbun corpora and the EDR bilingual dictionary.</Paragraph>
    <Paragraph position="1"> The recall of senses was 87% for senses whose ratios in the corpus were not less than 5%, and the accuracy of sense definitions was 77%.</Paragraph>
    <Paragraph position="2"> Acknowledgments: This research was supported by the New Energy and Industrial Technology Development Organization of Japan.</Paragraph>
  </Section>
class="xml-element"></Paper>