<?xml version="1.0" standalone="yes"?>
<Paper uid="W03-1803">
  <Title>Noun-Noun Compound Machine Translation: A Feasibility Study on Shallow Processing</Title>
  <Section position="7" start_page="4" end_page="4" type="concl">
    <SectionTitle>
6 Conclusion and future work
</SectionTitle>
    <Paragraph position="0"> This paper has used the NN compound translation task to establish performance upper bounds on shallow translation methods and in the process empirically determine the relative need for deep translation methods. We focused particularly on dictionary-driven MBMT and word-to-word compositional DMT, and demonstrated the relative strengths of each. When cascaded these two methods were shown to achieve 95%a62 coverage and potentially high translation accuracy. As such, shallow translation methods are able to translate the bulk of NN compound inputs successfully. null One question which we have tactfully avoided answering is how deep translation methods perform over the same data, and how successfully they can handle the data that shallow translation fails to produce a translation for. We leave these as items for future research. Also, we have deferred the issue of translation selection for the methods described here, and in future work hope to compare a range of translation selection methods using the data developed in this research.</Paragraph>
  </Section>
class="xml-element"></Paper>