<?xml version="1.0" standalone="yes"?>
<Paper uid="W96-0207">
  <Title>i Combining Hand-crafted Rules and Unsupervised Learning in Constraint-based Morphological Disambiguation</Title>
  <Section position="15" start_page="79" end_page="79" type="concl">
    <SectionTitle>
5 Conclusions
</SectionTitle>
    <Paragraph position="0"> This paper has presented a rule-based morphological disambiguation approach which combines a set of hand-crafted constraint rules and learns additional rules to choose and delete parses, from untagged text in an unsupervised manner. We have extended the rule learning and application schemes so that the impact of various morphological phenomena and features are selectively taken into account. We have applied our approach to the morphological disambiguation of Turkish, a free-constituent order language, with agglutinative morphology, exhibiting productive inflectional and derivational processes. We have also incorporated a rather sophisticated unknown form processor which extracts any relevant inflectional or derivational markers even if the root word is unknown.</Paragraph>
    <Paragraph position="1"> Our results indicate that by combining these hand-crafted, statistical and learned information sources, we can attain a recall of 96 to 97% with a corresponding precision of 93 to 94% and ambiguity of 1.02 to 1.03 parses per token, on test texts, however the impact of the rules that are learned is not significant as hand-crafted rules do most of the easy work at the initial stages.</Paragraph>
  </Section>
class="xml-element"></Paper>