<?xml version="1.0" standalone="yes"?>
<Paper uid="W98-1001">
  <Title>Discovering Lexical Information by Tagging Arabic Newspaper Text</Title>
  <Section position="11" start_page="5" end_page="5" type="concl">
    <SectionTitle>
8. CONCLUSION
</SectionTitle>
    <Paragraph position="0"> We badly need a large integrated comprehensive lexicon. To achieve this goal we need to build this lexicon automatically. To build such a lexicon we are developing a part of speech tagger for Arabic text that extracts features of the words encountered. We have described three major techniques that we are using in this paper: finding phrases, analyzing the affixes oftheword, and analyzing its patterns. We have classified the proper nouns in the Arabic language to different categories, we used a new technique to tag them from the Arabic text by using the ke3-words. We developed a set of grammatical rules for this reason.</Paragraph>
  </Section>
class="xml-element"></Paper>