<?xml version="1.0" standalone="yes"?>
<Paper uid="N03-1011">
  <Title>Learning Semantic Constraints for the Automatic Discovery of Part-Whole Relations</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> The method presented in this paper for the detection and validation of part-whole relation is semi-automatic and has a better accuracy than the previous attempts (Charniak, 1999). It discovers semi-automatically the part-whole lexico-syntactic patterns and learns (automatically) the semantic constraints needed for the disambiguation of these generally applicable patterns.</Paragraph>
    <Paragraph position="1"> We combined the results of the decision tree learning with an IS-A hierarchy (the WordNet IS-A relation) specialization for a more accurate learning.</Paragraph>
    <Paragraph position="2"> The method presented in this paper can be generalized to discover other semantic relations. The only part-whole elements used in this algorithm were the patterns and the training examples. Thus the learning procedure and the validation procedure are generally applicable and we intend to use the method for the detection of other semantic relations such as manner, influence, and others. The inconvenience of the method is that for a very precise learning the number of examples (both positive and negative) should be very large.</Paragraph>
    <Paragraph position="3"> We also intend to automate the detection of lexico-syntactic patterns and to discover constraints for all the part-whole patterns.</Paragraph>
  </Section>
class="xml-element"></Paper>