<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1127">
  <Title>Cross-lingual Information Extraction System Evaluation</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> We discussed the difficulty in cross-lingual information extraction caused by the translation of the source documents using an MT system. The experimental result for entity extraction suggests that exploiting some basic tools available for the source language will boost the performance of the whole CLIE system.</Paragraph>
    <Paragraph position="1"> We intend to investigate whether further performance gain may be obtained by introducing additional techniques for query translation. These techniques, including query translation on expanded queries and building a translation dictionary from parallel corpora, are currently used in crosslingual information retrieval (Larkey and Connell, 2003).</Paragraph>
  </Section>
class="xml-element"></Paper>