<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1617">
  <Title>Semantic Role Labeling of NomBank: A Maximum Entropy Approach</Title>
  <Section position="8" start_page="143" end_page="143" type="evalu">
    <SectionTitle>
6 Discussion and future work
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="143" end_page="143" type="sub_section">
      <SectionTitle>
6.1 Comparison of the composition of
PropBank and NomBank
</SectionTitle>
      <Paragraph position="0"> Counting the number of annotated predicates, the size of the September 2005 release of NomBank (NomBank.0.8) is about 83% of PropBank release  1. Preliminary consistency tests reported in (Mey null ers et al., 2004c) shows that NomBank's inter-annotator agreement rate is about 85% for core arguments and lower for adjunct arguments. The inter-annotator agreement for PropBank reported in (Palmer et al., 2005) is above 0.9 in terms of the Kappa statistic (Sidney and Castellan Jr., 1988). While the two agreement measures are not directly comparable, the current NomBank.0.8 release documentation indicates that only 32 of the most frequently occurring nouns in PTB II have been adjudicated.</Paragraph>
      <Paragraph position="1"> We believe the smaller size of NomBank.0.8 and the potential noise contained in the current release of the NomBank data may partly explain our lower SRL accuracy on NomBank, especially in the argument identification phase, as compared to the published accuracies of PropBank-based SRL systems.</Paragraph>
    </Section>
    <Section position="2" start_page="143" end_page="143" type="sub_section">
      <SectionTitle>
6.2 Difficulties in NomBank SRL
</SectionTitle>
      <Paragraph position="0"> The argument structure of nominalization phrases is less fixed (i.e., more flexible) than the argument structure of verbs. Consider again the example given in the introduction, we find the following flexibility in forming grammatical NomBank argument structures for &amp;quot;replacement&amp;quot;: * The positions of the arguments are flexible, so that &amp;quot;Greenspan's replacement Ben Bernanke&amp;quot;, &amp;quot;Ben Bernanke's replacement of Greenspan&amp;quot; are both grammatical.</Paragraph>
      <Paragraph position="1"> * Arguments can be optional, so that &amp;quot;Greenspan's replacement will assume the post soon&amp;quot;, &amp;quot;The replacement Ben Bernanke will assume the post soon&amp;quot;, and &amp;quot;The replacement will assume the post soon&amp;quot; are all grammatical.</Paragraph>
      <Paragraph position="2"> With the verb predicate &amp;quot;replace&amp;quot;, except for &amp;quot;Greenspan was replaced&amp;quot;, there is no freedom of forming phrases like &amp;quot;Ben Bernanke replaces&amp;quot; or simply &amp;quot;replaces&amp;quot; without supplying the necessary arguments to complete the grammatical structure.</Paragraph>
      <Paragraph position="3"> We believe the flexible argument structure of NomBank noun predicates contributes to the lower automatic SRL accuracy as compared to that of the PropBank SRL task.</Paragraph>
    </Section>
    <Section position="3" start_page="143" end_page="143" type="sub_section">
      <SectionTitle>
6.3 Integrating PropBank and NomBank
SRL
</SectionTitle>
      <Paragraph position="0"> Work in (Pustejovsky et al., 2005) discussed the possibility of merging various Treebank annotation efforts including PropBank, NomBank, and others. Future work involves studying ways of concurrently producing automatic PropBank and NomBank SRL, and improving the accuracy by exploiting the inter-relationship between verb predicate-argument and noun predicate-argument structures.</Paragraph>
      <Paragraph position="1"> Besides the obvious correspondence between a verb and its nominalizations, e.g., &amp;quot;replace&amp;quot; and &amp;quot;replacement&amp;quot;, there is also correspondence between verb predicates in PropBank and support verbs in NomBank. Statistics from NomBank sections 02-21 show that 86% of the support verbs in NomBank are also predicate verbs in PropBank.</Paragraph>
      <Paragraph position="2"> When they coincide, they share 18,250 arguments of which 63% have the same argument class in  to jointly improve PropBank and NomBank SRL accuracy.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>