<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1031">
  <Title>Word to word alignment strategies</Title>
  <Section position="6" start_page="65" end_page="65" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> According to our results different alignment strategies can be chosen to suit particular needs. Concluding from the experiments, restrictive methods like the intersection of directional alignments or competitive linking should be chosen if results with high precision are required (which are mostly found among one-to-one word links). This is, for example, the case in automatic extraction of bilingual lexicons where noise should be avoided as much as possible. A strong disadvantage of these approaches is that they do not include MWUs at all. Other strategies should be chosen for applications, which require a comprehensive coverage as, for example, machine translation. Symmetric approaches such as the refined combination of directional alignments and the constrained best-first alignment strategy yield the highest overall performance. They produce the best balance between precision and recall and the highest scores in terms of F-values.</Paragraph>
  </Section>
class="xml-element"></Paper>