<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-1520">
  <Title>Statistical Shallow Semantic Parsing despite Little Training Data</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
1 Introduction and Related Work
</SectionTitle>
    <Paragraph position="0"> Natural language understanding is an essential module in any dialogue system. To obtain satisfactory performance levels, a dialogue system needs a semantic parser/natural language understanding system (NLU) that produces accurate and detailed dialogue oriented semantic output. Recently, a number of semantic parsers trained using either the FrameNet (Baker et al., 1998) or the Prop-Bank (Kingsbury et al., 2002) have been reported.</Paragraph>
    <Paragraph position="1"> Despite their reasonable performances on general tasks, these parsers do not work so well in specific domains. Also, where these general purpose parsers tend to provide case-frame structures, that include the standard core case roles (Agent, Patient, Instrument, etc.), dialogue oriented domains tend to require additional information about addressees, modality, speech acts, etc. Where general-purpose resources such as PropBank and Framenet provide invaluable training data for general case, it tends to be a problem to obtain enough training data in a specific dialogue oriented domain.</Paragraph>
    <Paragraph position="2"> We in this paper propose and compare a number of approaches for building a statistically trained domain specific parser/NLU for a dialogue system.</Paragraph>
    <Paragraph position="3"> Our NLU is a part of Mission Rehearsal Exercise (MRE) project (Swartout et al., 2001). MRE is a large system that is being built to train experts, in which a trainee interacts with a Virtual Human using voice input. The purpose of our NLU is to convert the sentence strings produced by the speech recognizer into internal shallow semantic frames composed of slot-value pairs, for the dialogue module.</Paragraph>
  </Section>
class="xml-element"></Paper>