<?xml version="1.0" standalone="yes"?>
<Paper uid="E06-2013">
  <Title>Automatic Annotation for All Semantic Layers in FrameNet</Title>
  <Section position="7" start_page="136" end_page="137" type="evalu">
    <SectionTitle>
5 Evaluation
</SectionTitle>
    <Paragraph position="0"> We applied the system to a test set consisting of approximately 8,000 sentences.</Paragraph>
    <Paragraph position="1"> Because of inconsistent annotation, we did not evaluate the performance of detection of the EX-IST tag used in existential constructions. Preliminary experiments indicated that the performance was very poor.</Paragraph>
    <Paragraph position="2"> The results, with confidence intervals at the 95% level, are shown in Table 2. They demonstrate that the classical approach for FE identification, thatisclassification ofnodes intheparse tree, is as well a viable method for detection of other kinds of semantic information. The detection of X shows the poorest performance. This is to be expected, since it is very dependent on a GOV to have been detected in the first stage.</Paragraph>
    <Paragraph position="3"> The results for detection of aspectual particles is not very reliable (the confidence interval was +-0.17 for precision and +-0.19 for recall), since test corpus contained just 25 of these particles.</Paragraph>
  </Section>
class="xml-element"></Paper>