<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-1025">
  <Title>Automatic Measurement of Syntactic Development in Child Language</Title>
  <Section position="8" start_page="203" end_page="203" type="concl">
    <SectionTitle>
6 Conclusion and Future Work
</SectionTitle>
    <Paragraph position="0"> We have presented an automatic way to annotate transcripts of child language with the CHILDES syntactic annotation scheme. By using existing resources and a small amount of annotated data, we achieved state-of-the-art accuracy levels.</Paragraph>
    <Paragraph position="1"> GR identification was then used to automate the computation of IPSyn scores to measure grammatical development in children. The reliability of our automatic IPSyn was very close to the inter-rater reliability among human scorers, and far higher than that of the only other computational implementation of IPSyn. This demonstrates the value of automatic GR assignment to child language research.</Paragraph>
    <Paragraph position="2"> From the analysis in section 5.3, it is clear that the identification of certain GRs needs to be made more accurately. We intend to annotate more in-domain training data for GR labeling, and we are currently investigating the use of other applicable GR parsing techniques.</Paragraph>
    <Paragraph position="3"> Finally, IPSyn score calculation could be made more accurate with the knowledge of the expected levels of precision and recall of automatic assignment of specific GRs. It is our intuition that in a number of cases it would be preferable to trade recall for precision. We are currently working on a framework for soft-labeling of GRs, which will allow us to manipulate the precision/recall trade-off as discussed in (Carroll and Briscoe, 2002).</Paragraph>
  </Section>
class="xml-element"></Paper>