<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-1040">
  <Title>Feature-Rich Statistical Translation of Noun Phrases</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> We have shown that noun phrase translation can be separated out as a subtask. Our manual experiments show that NP/PPs can almost always be translated as NP/PPs across many languages, and that the translation of NP/PPs usually does not require additional external context.</Paragraph>
    <Paragraph position="1"> We also demonstrated that the reduced complexity of noun phrase translation allows us to address the problem in a maximum entropy reranking framework, where we only consider the 100-best candidates of a base translation system. This enables us to introduce any features that can be computed over a full translation pair, instead of being limited to features that can be integrated into the search algorithm of the decoder, which only has access to partial translations.</Paragraph>
    <Paragraph position="2"> We improved performance of noun phrase translation by 12.3% by using a phrase translation model, a maximum entropy reranking method and addressing specific properties of noun phrase translation: compound splitting, using the web as a language model, and syntactic features. We showed not only improvement on NP/PP translation over best known methods, but also improved overall sentence translation quality.</Paragraph>
    <Paragraph position="3"> Our long term goal is to address additional syntactic constructs in a similarly dedicated fashion. The next step would be verb clauses, where modeling of the subcategorization of the verb is important.</Paragraph>
  </Section>
class="xml-element"></Paper>