<?xml version="1.0" standalone="yes"?>
<Paper uid="H89-2028">
  <Title>Advisory Committee:</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
ABSTRACT
</SectionTitle>
    <Paragraph position="0"> Spoken Language Systems will require integration of continuous speech recognition and natural language processing. This is a proposed specification for an interface between a continuous speech recognizer (CSR) and a natural language processor (NLP) to form a spoken language system.</Paragraph>
    <Paragraph position="1"> Both components are integrated with a stack controller and contribute to the search control. The specification also defines a &amp;quot;Top-N&amp;quot; mode in which a &amp;quot;first part&amp;quot; outputs a list of top N scored sentences for postprocessing by a &amp;quot;second part&amp;quot;. An additional use for this specification might be NLP evaluation testing: a common simulated CSR could be interfaced to each site's NLP to provide identical testing environments.</Paragraph>
  </Section>
class="xml-element"></Paper>