<?xml version="1.0" standalone="yes"?>
<Paper uid="C92-1023">
  <Title>STOCK OF SHARED KNOWLEDGE - - A TOOL FOR SOLVING PRONOMINAL ANAPHORA</Title>
  <Section position="11" start_page="0" end_page="0" type="concl">
    <SectionTitle>
5. CONCLUSION
</SectionTitle>
    <Paragraph position="0"> The previous analysis has been done for Czech.</Paragraph>
    <Paragraph position="1"> We are far from claiming that every language would ACT~ DE COLING-92, NANTES, 23-28 AOU'r 1992 I 3 2 PROC. OF COLING-92, NANTES, AUG. 23-28, 1992 reflect the same relations between factors which can help to solve the pronominal anaphora. We have only tried to show how certain factors can result in a more sophisticated treatment of anaphora in NLP.</Paragraph>
    <Paragraph position="2"> Our mechanism is designed as an open system, the nature of all functions mentioned here enables to add any number of other phenomena which can help to solve the problem of anaphora re.solution.</Paragraph>
    <Paragraph position="3"> Our approach is substantially different from the approach of e.g. Alshawi (1987) or Rich, Luper-Foy (1987). Our system does not need any knowledge base except the special thesaurus of related notions. It would be very interesting to combine our approach and the approach of Alshawi in some experimental NLP system.</Paragraph>
  </Section>
class="xml-element"></Paper>