<?xml version="1.0" standalone="yes"?>
<Paper uid="W03-0302">
  <Title>ProAlign: Shared Task System Description</Title>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
4 Multiple Alignments
</SectionTitle>
    <Paragraph position="0"> The result of the constrained alignment search is a highprecision, word-to-word alignment. We then relax the word-to-word constraint, and use statistics regarding collocations with unaligned words in order to make many-to-one alignments. We also employ a further relaxed linking process to catch some cases where the cohesion constraint ruled out otherwise good alignments. These auxiliary methods are currently not integrated into our search or our probability model, although that is certainly a direction for future work.</Paragraph>
  </Section>
class="xml-element"></Paper>