<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0627">
  <Title>Semantic Role Lableing System using Maximum Entropy Classi er [?]</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The semantic role labeling (SRL) is to assign syntactic constituents with semantic roles (arguments) of predicates (most frequently verbs) in sentences.</Paragraph>
    <Paragraph position="1"> A semantic role is the relationship that a syntactic constituent has with a predicate. Typical semantic arguments include Agent, Patient, Instrument, etc.</Paragraph>
    <Paragraph position="2"> and also adjunctive arguments indicating Locative, Temporal, Manner, Cause, etc. It can be used in lots of natural language processing application systems in which some kind of semantic interpretation is needed, such as question and answering, information extraction, machine translation, paraphrasing, and so on.</Paragraph>
    <Paragraph position="3"> [?]This research was supported by National Natural Science Foundation of China via grant 60435020 Last year, CoNLL-2004 hold a semantic role labeling shared task (Carreras and M arquez, 2004) to test the participant systems' performance based on shallow syntactic parser results. In 2005, SRL shared task is continued (Carreras and M arquez, 2005), because it is a complex task and now it is far from desired performance.</Paragraph>
    <Paragraph position="4"> In our SRL system, we select maximum entropy (Berger et al., 1996) as a classi er to implement the semantic role labeling system. Different from the best classi er reported in literatures (Pradhan et al., 2005) support vector machines (SVMs) (Vapnik, 1995), it is much easier for maximum entropy classi er to handle the multi-class classi cation problem without additional post-processing steps. The classi er is much faster than training SVMs classi ers. In addition, maximum entropy classi er can be tuned to minimize over- tting by adjusting gaussian prior. Xue and Palmer (2004; 2005) and Kwon et al. (2004) have applied the maximum entropy classi er to semantic role labeling task successfully.</Paragraph>
    <Paragraph position="5"> In the following sections, we will describe our system and report our results on development and test sets.</Paragraph>
  </Section>
class="xml-element"></Paper>