<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-2923">
  <Title>LingPars, a Linguistically Inspired, Language-Independent Machine Learner for Dependency Treebanks</Title>
  <Section position="7" start_page="174" end_page="174" type="concl">
    <SectionTitle>
5 Outlook
</SectionTitle>
    <Paragraph position="0"> We have shown that a probabilistic dependency parser can be built on CG-inspired linguistic prin ciples with a strong focus on function and tag se quences. Given the time constraint and the fact that the learner had to be built from scratch, its perfor mance would encourage further research. In partic ular, a systematic parameter/performance analysis13 should be performed for the individual languages.</Paragraph>
    <Paragraph position="1"> In the long term, a notational harmonization of the treebanks should allow the learner to be seeded with existing hand-written dependency rules.</Paragraph>
  </Section>
class="xml-element"></Paper>