<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-2421">
  <Title>Semantic Role Labeling Via Generalized Inference Over Classifiers</Title>
  <Section position="6" start_page="0" end_page="0" type="evalu">
    <SectionTitle>
5 Results
</SectionTitle>
    <Paragraph position="0"> In this section, we present results. For the second phase, we evaluate the quality of the phrase predictor. The result first evaluates the phrase classifier, given the perfect phrase locations without using inference (i.e. F(PM) = PM). The second, adds inference to the phrase classification over the perfect classifiers (see Table 2). We evaluate the overall performance of our system (without assuming perfect phrases) by training and evaluating the phrase classifier on the output from the first phase (see Table 3).</Paragraph>
    <Paragraph position="1"> Finally,since this is a tagging task, we compare this system with the basic tagger that we have, the CLCL  The phrase scoring is choosen from either the first phase or the second phase and each is evaluated by considering simply non-overlapping constraints or the full set of linguistic constraints. To make a fair comparison, parameters were set seperately to optimize performance when using the first phase results. All results are for overall performance.</Paragraph>
    <Paragraph position="2">  ference assuming perfect boundary detection in the first phase. Inference improves performance by restricting label sequences rather than restricting structural properties since the correct boundaries are given. All results are for overall performance on the development set.</Paragraph>
    <Paragraph position="3"> shallow parser from (Punyakanok and Roth, 2001), which is equivalent to using the scoring function from the first phase with only the non-overlapping constraints. Table 1 shows how how additional constraints over the standard non-overlapping constraints improve performance on the development set4.</Paragraph>
  </Section>
class="xml-element"></Paper>