<?xml version="1.0" standalone="yes"?>
<Paper uid="C02-1086">
  <Title>Implicit Ambiguity Resolution Using Incremental Clustering in Korean-to-English Cross-Language Information Retrieval</Title>
  <Section position="5" start_page="2" end_page="2" type="concl">
    <SectionTitle>
4 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have proposed the method of applying dynamic incremental clustering to the implicit resolution of query ambiguities in Korean-to-English cross-language information retrieval. The method used the clusters of  retrieved documents as a context for re-weighting each retrieved document and for re-ranking the retrieved documents.</Paragraph>
    <Paragraph position="1"> Our method was evaluated on TREC-6 CLIR test collection. This method achieved 28.29% performance improvement for translated queries without ambiguity resolution. This corresponds to 97.27% of the monolingual performance.</Paragraph>
    <Paragraph position="2"> When our method was used with the query ambiguity resolution method based on mutual information, it showed 105.87% performance improvement of the monolingual retrieval.</Paragraph>
    <Paragraph position="3"> These results indicate that cluster analysis help to resolve ambiguity greatly, and each cluster itself provide a context for a query.</Paragraph>
    <Paragraph position="4"> Our method is a language independent model which can be applied to any language retrieval. We expect that our method will further improve the results, although further research is needed on combining a method to improve recall such as query expansion and relevance feedback.</Paragraph>
  </Section>
class="xml-element"></Paper>