<?xml version="1.0" standalone="yes"?>
<Paper uid="C80-1056">
  <Title>HOW TO DEAL WITH AMBIGUITIES WHILE PARSING: EXAM --- A SEMANTIC PROCESSING SYSTEM FOR JAPANESE LANGUAGE</Title>
  <Section position="6" start_page="372" end_page="372" type="concl">
    <SectionTitle>
5. CONCLUSION
</SectionTitle>
    <Paragraph position="0"> We have discussed the procedures by which EXAM deals with ambiguities. This constitutes a difficult task for an NLUS and the trivial method of asking the user to choose one of several possible interpretations has been adopted. In dealing with ambiguities, EXAM avoids the combinatorial explosion of possible interpretations by means of several devices. We classify ambiguities into two categories, that is, ambiguity in sense and ambiguity in meaning. EXAM adopts the strategy of first processing sense representations, and secondly meaning representations; the parsing process is carried out in an essentially breadth-first manner.</Paragraph>
    <Paragraph position="1"> However, EXAM does not completely clarify ambiguities in meaning, especially ambiguities which are not resolved by the preceding context.</Paragraph>
    <Paragraph position="2"> This constitutes a problem which still awaits solution.</Paragraph>
  </Section>
class="xml-element"></Paper>