<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-2606">
  <Title>Reranking Translation Hypotheses Using Structural Properties</Title>
  <Section position="6" start_page="46" end_page="47" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> We added syntactically motivated features to a statistical machine translation system in a reranking framework. The goal was to analyze whether shallow parsing techniques help in identifying ungrammatical hypotheses. We showed that some improvements are possible by utilizing supertagging, lightweight dependency analysis, a link  grammar parser and a maximum-entropy based chunk parser. Adding features to n-best lists and discriminatively training the system on a development set helped to gain up to 0.7% in BLEU score on the test set.</Paragraph>
    <Paragraph position="1"> Future work could include developing an adapted LTAG for the BTEC domain or incorporating n-gram models into the link grammar concept in order to derive a long-range language model (Lafferty et al., 1992). However, we feel that the current improvements are not significant enough to justify these efforts. Additionally, we will apply these reranking methods to larger corpora in order to study the effects on longer sentences from more complex domains.</Paragraph>
  </Section>
class="xml-element"></Paper>