<?xml version="1.0" standalone="yes"?>
<Paper uid="C02-1065">
  <Title>Measuring the Similarity between Compound Nouns in Difierent Languages Using Non-Parallel Corpora</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> We proposed a method that measures the similarity between compound nouns in difierent languages by contextual information from non-parallel corpora. The method efiectively selects translation candidates although it uses unrelated corpora in difierent languages. It measures the similarity between relatively frequent words using context word vector. As for less commonco-occurrencewords, contextattribute vectors compensate for the lack of information.</Paragraph>
    <Paragraph position="1">  Forfuturework,wewillinvestigatewaysofintegrating the method and other information, e.g., similarity of components, to improve precision.</Paragraph>
  </Section>
class="xml-element"></Paper>