<?xml version="1.0" standalone="yes"?>
<Paper uid="H05-1022">
  <Title>Machine Intelligence Lab, Cambridge University Engineering Department</Title>
  <Section position="8" start_page="175" end_page="175" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have described word-to-phrase alignment models capable of good quality bitext word alignment.</Paragraph>
    <Paragraph position="1"> In Arabic-English and Chinese-English translation and alignment they compare well to Model-4, even with large bitexts. The model architecture was inspired by features of Model-4, such as fertility and distortion, but care was taken to ensure that dynamic programming procedures, such as EM and Viterbi alignment, could still be performed. There is practical value in this: training and alignment are easily parallelized. Working with HMMs also makes it straightforward to explore new modeling approaches. We show an augmentation scheme that adds to phrases extracted from Viterbi alignments; this improves translation with both the WtoP and the Model-4 phrase pairs, even though it would be infeasible to implement the scheme under Model-4 itself. We note that these models are still relatively simple, and we anticipate further alignment and translation improvement as the models are refined.</Paragraph>
  </Section>
class="xml-element"></Paper>