<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-0707">
  <Title>Incorporating Position Information into a Maximum Entropy/Minimum Divergence Translation Model</Title>
  <Section position="5" start_page="40" end_page="41" type="concl">
    <SectionTitle>
4 Conclusion
</SectionTitle>
    <Paragraph position="0"> This paper deals with the problem of incorporating information about the positions of bilingual word pairs into a MEMD model which is analogous to the classical IBM model 1, thereby creating a MEMD analog to the IBM model 2. I proposed and evaluated two methods for accomplishing this: using IBM2 position parameter probabilities as MEMD feature values, which  ious MEMD2B models. Each connected line in this graph corresponds to a vertical column of search points in figure 1.</Paragraph>
    <Paragraph position="1"> capture the occurrence of a word-pair with a MEMD1 weight that falls into a specific range of values at a position to which IBM2 assigns a probability in a certain range. The second model achieved over 40% lower test perplexity than a linear combination of a trigram and IBM2, despite using several orders of magnitude fewer parameters.</Paragraph>
    <Paragraph position="2"> This work represents a novel approach to translation modeling which is most appropriate for applications like TransType which need to make rapid predictions of upcoming text. However, it is not inconceivable that it could also be used for full-fledged MT. One partial impediment to this is that the MEMD framework lacks  a mechanism equivalant to the EM algorithm for estimating probabilities associated with hidden variables. The solution I have proposed here can be seen as a first step to investigating ways of getting around this problem.</Paragraph>
  </Section>
class="xml-element"></Paper>