<?xml version="1.0" standalone="yes"?>
<Paper uid="C02-1027">
  <Title>Shallow language processing architecture for Bulgarian</Title>
  <Section position="6" start_page="0" end_page="0" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> This paper outlines the development of the first robust and shallow text processing framework in Bulgarian LINGUA which includes modules for tokenisation, sentence splitting, paragraph segmentation, part-of-speech tagging, clause chunking, noun phrases extraction and anaphora resolution (Figure 1). Apart from the module on pronoun resolution which was adapted from Mitkov's knowledge-poor approach for English and the incorporation of BULMORPH in the part-of-speech tagger, all modules were specially built for LINGUA. The evaluation shows promising results for each of the modules.</Paragraph>
    <Paragraph position="1"> 7The optimisation made use of genetic algorithms in a manner similar to that described in (Orasan et al., 2000).</Paragraph>
  </Section>
class="xml-element"></Paper>