<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1518">
  <Title>Using LTAG-Based Features for Semantic Role Labeling</Title>
  <Section position="8" start_page="131" end_page="131" type="concl">
    <SectionTitle>
6 Conclusion and Future Work
</SectionTitle>
    <Paragraph position="0"> In this paper, we proposed a novel model for SRL using features extracted from LTAG derivation trees. A simple decision list learner is applied to train on the tree patterns containing new features. This simple learning method enables us to quickly explore new features for this task. However, this work is still preliminary: a lot of additional work is required to be competitive with the state-of-the-art SRL systems. In particular, we do not deal with automatically parsed data yet, which leads to a drop in our performance. We also do not incorporate various other features commonly used for SRL, as our goal in this paper was to make a direct comparison between simple pattern matching features on the derived tree and compare them to features from LTAG derivation trees.</Paragraph>
  </Section>
class="xml-element"></Paper>