<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1518">
  <Title>Using LTAG-Based Features for Semantic Role Labeling</Title>
  <Section position="4" start_page="0" end_page="127" type="intro">
    <SectionTitle>
2 Background about SRL
</SectionTitle>
    <Paragraph position="0"> A semantic role is defined to be the relationship that a syntactic constituent has with the predicate.</Paragraph>
    <Paragraph position="1"> For example, the following sentence, taken from the PropBank corpus, shows the annotation of semantic roles: [A0 Late buying] [V gave] [A2 the Paris Bourse] [A1 a parachute] [AM-TMP after its free fall early in the day].</Paragraph>
    <Paragraph position="2"> Here, the arguments for the predicate gave are defined in the PropBank Frame Scheme (Palmer, Gildea and Kingsbury, 2005) as: V: verb A2: beneficiary A0: giver AM-TMP: temporal A1: thing given Recognizing and labeling semantic arguments is a key task for answering &amp;quot;Who&amp;quot;, &amp;quot;When&amp;quot;,&amp;quot;What&amp;quot;, &amp;quot;Where&amp;quot;, &amp;quot;Why&amp;quot;, etc. questions in Information Extraction, Question Answering, Summarization (Melli et al, 2005), and, in general, in all NLP tasks in which some kind of semantic interpretation is needed.</Paragraph>
    <Paragraph position="3"> Most previous research treats the semantic role labeling task as a classification problem, and divides it into two phases: argument identification and argument classification. Argument identification involves classifying each syntactic element in a sentence into either an argument or a nonargument. Argument classification involves classifying each argument identified into a specific semantic role. A variety of machine learning methods have been applied to this task. One of the most important steps in building an accurate classifier is feature selection. Different from the widely used  feature functions that are based on the syntactic parse tree (Gildea and Jurafsky, 2002), we explore the use of LTAG-based features in a simple discriminative decision-list learner.</Paragraph>
  </Section>
class="xml-element"></Paper>