<?xml version="1.0" standalone="yes"?>
<Paper uid="E93-1021">
  <Title>Towards a proper treatment of coercion phenomena *</Title>
  <Section position="7" start_page="175" end_page="176" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> While it is generally held that natural langage proceasing can only benefit from taking into account &amp;quot;non literal&amp;quot; meaning, i.e. phenomena pertaining to metaphor, metonymy, and coercion, there is no agreement on the best way to attack them. We have addressed here the problem of coercion, which seems to entail a &amp;quot;strong&amp;quot; type shift (from o to e), while metonymy is more properly analyzed as a codified facet shift inside complex structures, and metaphor is generally conceived as based over analogy. The very nature of coercion phenomena suggests that tasks such as studying types hierarchies and methods for positioning lexical items in these hierarchies are pre-requisites for an acceptable treatment. It is likely that the use of thesauri, and more generally of lexical descriptive tools, will prove helpful. Our future research is oriented in this direction. We do not ex- null pect to find &amp;quot;rules&amp;quot; in a strong sense, that is, fixed procedures that would lend themselves to a simple algorithmic adaptation, but rather complex systems of constraints, whose study should allow to organize the descriptive tools in a more rigorous and principled way.</Paragraph>
  </Section>
class="xml-element"></Paper>