<?xml version="1.0" standalone="yes"?>
<Paper uid="W02-0503">
  <Title>Acquisition System for Arabic Noun Morphology</Title>
  <Section position="6" start_page="0" end_page="0" type="evalu">
    <SectionTitle>
6 Results
</SectionTitle>
    <Paragraph position="0"> To test our system we used nouns obtained from a corpus developed by Ahmad Hasnah based on text given to Illinois Institute of Technology, by the newspaper, Al-Raya, published in Qatar. We have tested each module in our system: the suffix analyzer modules, the pattern generator module, and the user-Feedback module. Table 7 shows the result of testing the system on 500 nouns.</Paragraph>
    <Paragraph position="1">  As shown in Table 7 there were ten failure because of incorrect suffix analysis and 29 due to missing patterns. These missing patterns have now been added. The suffix analysis problem is hard to correct because it arises from underlying ambiguities. If the noun has been classified previously the system does not have any problem to identify it and identify any noun derived from it.</Paragraph>
    <Paragraph position="2"> The User-Feedback Module found most of the nouns that the Database Checker Module failed to identify. Table 8 shows a number of nouns identified by suffix/pattern, nouns identified by Database Checker Module and nouns identified by User-Feedback Modules.</Paragraph>
    <Paragraph position="3"> We believe that the more knowledge that the system gains and the more nouns that it adds to the Classified Noun Table the fewer questions have to be asked.</Paragraph>
  </Section>
class="xml-element"></Paper>