<?xml version="1.0" standalone="yes"?>
<Paper uid="H92-1096">
  <Title>DEVELOPMENT OF A SPOKEN LANGUAGE SYSTEM</Title>
  <Section position="1" start_page="0" end_page="0" type="metho">
    <SectionTitle>
DEVELOPMENT OF A SPOKEN LANGUAGE SYSTEM
</SectionTitle>
    <Paragraph position="0"/>
  </Section>
  <Section position="2" start_page="0" end_page="0" type="metho">
    <SectionTitle>
PROJECT GOALS
</SectionTitle>
    <Paragraph position="0"> The primary objective of this project is to develop a robust, high-performance spoken language system. We have achieved this by integrating the BYBLOS speech recognition system with the DELPHI natural language processing system to produce the HARC (Hear And Respond to Continuous speech) system.</Paragraph>
  </Section>
  <Section position="3" start_page="0" end_page="0" type="metho">
    <SectionTitle>
RECENT RESULTS
</SectionTitle>
    <Paragraph position="0"> Achieved a weighted error rate of 43.7 on the official ATIS spoken language system (SLS) evaluation for the Feburary, 1992 workshop.</Paragraph>
    <Paragraph position="1"> This is the lowest error rate of all systems evaluated.</Paragraph>
    <Paragraph position="2"> Achieved a word error rate of 9.4 on the official ATIS speech recognition (SPREC) evaluation for the February, 1992 workshop. This is the lowest error rate of all systems evaluated.</Paragraph>
    <Paragraph position="3"> Achieved a weighted error rate of 33.9 on the official ATIS natural language (NL) evaluation for the February, 1992 workshop. This is not significantly different from the other top-scoring systems.</Paragraph>
    <Paragraph position="4"> The 1-best output of BBN's speech recognition component, paired with SRI's natural language component, achieved an weighted error rate of 39.9.</Paragraph>
    <Paragraph position="5"> Achieved an unofficial weighted error on the Feburary, 1992 test set of 39.23, the lowest (though unofficial) rate of all systems we currently know of.</Paragraph>
    <Paragraph position="6"> We developed and used a data collection facility to collect 2277 utterances from 62 subjects. We were the only site to reach the data collection goals by the original deadline of 1 September.</Paragraph>
    <Paragraph position="7"> We completed an initial version of a new DELPHI NL system, which incorporates a semantic component integrated with the unification-based syntactic grammar, but separated from it. This allows for multiple semantic interpretations for a single parse, facilitates rule creation and debugging, and allows for both greater expressive power and greater computational efficiency.</Paragraph>
    <Paragraph position="8"> We developed a fallback understanding component for DELPHI which is composed of a fragment generator, a syntactic combiner, and a frame combiner. This fallback strategy was included in the system used in the official evaluation.</Paragraph>
    <Paragraph position="9"> For our real-time decoder work, we sped up the decoder so that it can run in real-rime with a higher beamwidth, and, therefore, higher accuracy.</Paragraph>
    <Paragraph position="10"> We ported the real-time speech system to run on the SGI workstation.</Paragraph>
    <Paragraph position="11"> We developed tools for creating and estimating various types of statistical grammars.</Paragraph>
  </Section>
  <Section position="4" start_page="0" end_page="463" type="metho">
    <SectionTitle>
PLANS FOR THE COMING YEAR
</SectionTitle>
    <Paragraph position="0"> For the coming year, we plan to continue our work on improving both the speech recognition perofrmance and the natural language processing performance of the HARC system. We will pay particular attention to the discourse phenomena that are so important in the ATIS domain, and will take increasing advantage of probabilistic analysis at several levels of processing. We will in particular investigate methods for automatic training of the NL component. We will also study more deeply the interaction of the speech and NL components via the N-best interface.</Paragraph>
  </Section>
class="xml-element"></Paper>