<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0829">
  <Title>Competitive Grouping in Integrated Phrase Segmentation and Alignment Model</Title>
  <Section position="6" start_page="160" end_page="161" type="evalu">
    <SectionTitle>
5 Experiments
</SectionTitle>
    <Paragraph position="0"> We participated the shared task in the WPT05 workshop2 and applied ISA to all four language pairs  (French-English, Finnish-English, German-English and Spanish-English). Table 1 shows the n-gram coverage of the dev-test set. French and Spanish data are better covered by the training data compared to the German and Finnish sets. Since our phrase alignment is constrained by the locality assumption and we can only extract phrase pairs of adjacent words, lower n-gram coverage will result in lower translation scores. We used the training data  the training data. Numbers in parenthesis are the actual counts of n-gram tokens in the dev-test data. and the language model as provided and manually tuned the parameters of the Pharaoh decoder3 to optimize BLEU scores. Table 2 shows the translation results on the dev-test and the test set of WPT05. The BLEU scores appear comparable to those of other state-of-the-art phrase alignment systems, in spite of the simplicity of the ISA model and ease of training.</Paragraph>
  </Section>
class="xml-element"></Paper>