<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1010">
  <Title>Named Entity Transliteration with Comparable Corpora</Title>
  <Section position="7" start_page="78" end_page="78" type="concl">
    <SectionTitle>
5 Conclusions and Future Work
</SectionTitle>
    <Paragraph position="0"> In this paper we have discussed the problem of Chinese-English name transliteration as one component of a system to find matching names in comparable corpora. We have proposed two methods for transliteration, one that is more traditional and based on phonetic correspondences, and one that is based on word distributions and adopts methods from information retrieval. We have shown  that both methods yield good results, and that even better results can be achieved by combining the methods. We have further showed that one can improve upon the combined model by using reinforcement via score propagation when transliteration pairs cluster together in document pairs. The work we report is ongoing. We are investigating transliterations among several language pairs, and are extending these methods to Korean, Arabic, Russian and Hindi -- see (Tao et al., 2006).</Paragraph>
  </Section>
class="xml-element"></Paper>