<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-3026">
  <Title>Multi-Engine Machine Translation Guided by Explicit Word Matching</Title>
  <Section position="7" start_page="103" end_page="103" type="concl">
    <SectionTitle>
5 Conclusions and Future Work
</SectionTitle>
    <Paragraph position="0"> Our MEMT algorithm shows consistent improvement in the quality of the translation compared any of the original systems. It scores better than an &amp;quot;oracle&amp;quot; that chooses the best original translation on a sentence-by-sentence basis. Furthermore, our MEMT algorithm produces hypotheses that are of yet even better quality, but our current scoring algorithm is not yet able to effectively select the best hypothesis. The focus of our future work will thus be on identifying features that support improved hypothesis scoring.</Paragraph>
  </Section>
class="xml-element"></Paper>