<?xml version="1.0" standalone="yes"?>
<Paper uid="C92-4201">
  <Title>AUT()MATI(; TRANSI,ATION OF NOUN COMPOUNI)S</Title>
  <Section position="9" start_page="0" end_page="0" type="concl">
    <SectionTitle>
4 Conclusions
</SectionTitle>
    <Paragraph position="0"> This paper demonstrates that the translation of noun compounds is a difficult task. llavlng German ms the source language adds the problem of segmenting the compound into its constituents, a prol)letn which does not exist in many o(her languages. The solution for these problems seems to require varloas levels of in for marion, involving morphological, syntactic, semantic and stylistic criteria.</Paragraph>
    <Paragraph position="1"> Though these levels are general for \[:very natural language processing task, WE have shown how a detailed analysis of the specific linguistic \[)hellorneu~t can lead to an ellicient hybrid architectnre which uses the partial information availalde computation ally. This architecture con,1)ines formal syntactic and mnrpltologlcal rules, wherever they (:an he spe(:ified accurately, with empirical data whicll reltects sorer: or the semantic and stylistic considerations. In this sense, this paper promotes the integration of the sometimes diverging streams, natnely the use of sylnhollo, manually stipulated linguistic ruk:s versus the use of statistical data which is extracted alltolnatically from corpora, ht our view, these two disciplines complement each other and are both esscntlal to aehleve high performance in practical natural \]an gllage processing systems.</Paragraph>
    <Paragraph position="2"> Acknowledgements: We wouhl like to thank Eran Amir from llai\[a, Peter t~rown from Yorktown and Mark Beers and Myriam Welsehhillig from llci delberg h)r their Itelp and comments.</Paragraph>
  </Section>
class="xml-element"></Paper>