<?xml version="1.0" standalone="yes"?>
<Paper uid="W03-1001">
  <Title>A Projection Extension Algorithm for Statistical Machine Translation</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper, we describe a block-based unigram model for SMT. A novel block learning algorithm is presented that extends high-precision interval projections by elements from a high-recall alignment.</Paragraph>
    <Paragraph position="1"> The extension method is shown to improve translation performance significantly. For the Chinese-to-English task, we obtained a NIST score of a193a51a192a189a7a194 on the June 2002 DARPA TIDES Large Data evaluation test set.</Paragraph>
  </Section>
class="xml-element"></Paper>