<?xml version="1.0" standalone="yes"?>
<Paper uid="H05-2004">
  <Title>Demonstrating an Interactive Semantic Role Labeling System</Title>
  <Section position="2" start_page="0" end_page="6" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Semantic parsing of sentences is believed to be an important subtask toward natural language understanding, and has immediate applications in tasks such information extraction and question answering.</Paragraph>
    <Paragraph position="1"> We study semantic role labeling (SRL), defined as follows: for each verb in a sentence, the goal is to identify all constituents that fill a semantic role, and to determine their roles (such as Agent, Patient or Instrument) and their adjuncts (such as Locative, Temporal or Manner). The PropBank project (Kingsbury and Palmer, 2002), which provides a large human-annotated corpus of semantic verb-argument relations, has opened doors for researchers to apply machine learning techniques to this task.</Paragraph>
    <Paragraph position="2"> The focus of the research has been on improving the performance of the SRL system by using, in addition to raw text, various syntactic and semantic information, e.g. Part of Speech (POS) tags, chunks, clauses, syntactic parse tree, and named entities, which is found crucial to the SRL system (Punyakanok et al., 2005).</Paragraph>
    <Paragraph position="3"> In order to support a real world application such as an interactive question-answering system, the ability of an SRL system to analyze text in real time is a necessity. However, in previous research, the overall efficiency of the SRL system has not been considered. At best, the efficiency of an SRL system may be reported in an experiment assuming that all the necessary information has already been provided, which is not realistic. A real world scenario requires the SRL system to perform all necessary preprocessing steps in real time. The overall efficiency of SRL systems that include the preprocessors is not known.</Paragraph>
    <Paragraph position="4"> Our demonstration aims to address this issue. We present an interactive system that performs the SRL task from raw text in real time. Its architecture is based on the top system in the 2005 CoNLL shared task (Koomen et al., 2005), modified to process raw text using lower level processors but maintaining  good real time performance.</Paragraph>
  </Section>
class="xml-element"></Paper>