<?xml version="1.0" standalone="yes"?>
<Paper uid="W98-1418">
  <Title>GENERATION OF NOUN COMPOUNDS IN HEBREW: CAN SYNTACTIC KNOWLEDGE BE FULLY ENCAPSULATED?</Title>
  <Section position="7" start_page="175" end_page="176" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have presented in this paper basic data on the Hebrew smixut construction. Our strategy to implement smixut in the HUGG syntactic realization is to provide a simple semantic classification in the input. We have demonstrated the many benefits this classification has within the realization process.</Paragraph>
    <Paragraph position="1"> Two main problems have been traditionally associated with such semantic accounts of nouncompounding: the relations are not well-defined enough and they are not necessary nor sufficient to explain all uses of compounding. We address these two problems in three ways: (1) we provide an empirical evaluation demonstrating high coder agreement when labeling complex NPs with the set of relations we identify; (2) we demonstrate empirically that the default strategy of &amp;quot;generating a smixut when a semantic relation licenses it&amp;quot; corresponds with the observed usage of smixut in more than 95% of the cases; and (3) we allow the pragmatic module to add a feature use-smixut in the input.</Paragraph>
    <Paragraph position="2">  The same set of semantic relations is now being used in an extension to SURGE to allow similar paraphrasing decisions in English.</Paragraph>
  </Section>
class="xml-element"></Paper>