<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-2606">
  <Title>Reranking Translation Hypotheses Using Structural Properties</Title>
  <Section position="3" start_page="0" end_page="41" type="intro">
    <SectionTitle>
2 Related work
</SectionTitle>
    <Paragraph position="0"> In (Och et al., 2004), the effects of integrating syntactic structure into a state-of-the-art statistical machine translation system are investigated. The approachissimilartotheapproachpresentedhere:  firstly, a word graph is generated using the base-line SMT system and n-best lists are extracted accordingly, then additional feature functions representingsyntacticknowledgeareaddedandthecor- null responding scaling factors are trained discriminatively on a development n-best list.</Paragraph>
    <Paragraph position="1"> Och and colleagues investigated a large amount of different feature functions. The field of application varies from simple syntactic features, such as IBM model 1 score, over shallow parsing techniques to more complex methods using grammars and intricate parsing procedures. The results were rather disappointing. Only one of the simplest models, i.e. the implicit syntactic feature derived from IBM model 1 score, yielded consistent and significant improvements. All other methods had only a very small effect on the overall performance. null</Paragraph>
  </Section>
class="xml-element"></Paper>