<?xml version="1.0" standalone="yes"?>
<Paper uid="E06-1012">
  <Title>Statistical Dependency Parsing of Turkish</Title>
  <Section position="7" start_page="95" end_page="95" type="concl">
    <SectionTitle>
7 Conclusions
</SectionTitle>
    <Paragraph position="0"> We have presented our results from statistical dependency parsing of Turkish with statistical models trained from the sentences in the Turkish treebank. The dependency relations are between sub-lexical units that we call inflectional groups (IGs) and the parser recovers dependency relations between these IGs. Due to the modest size of the treebank available to us, we have used unlexicalized statistical models, representing IGs by reduced representations of their morphological properties. For the purposes of this work we have limited ourselves to sentences with all left-to-right dependency links that do not cross each other.</Paragraph>
    <Paragraph position="1"> Weget our best results (73.5% IG-to-IG link accuracy) using a model where IGs are used as units for parsing and we use as contexts, word final IGs of the words before and after the dependent.</Paragraph>
    <Paragraph position="2"> Future work involves a more detailed understanding of the nature of the errors and see how limited lexicalization can help, as well as investigation of more sophisticated models such as SVM or memory-based techniques for correctly identifying dependencies.</Paragraph>
  </Section>
class="xml-element"></Paper>