<?xml version="1.0" standalone="yes"?>
<Paper uid="P99-1074">
  <Title>Robust, Finite-State Parsing for Spoken Language Understanding</Title>
  <Section position="9" start_page="577" end_page="577" type="concl">
    <SectionTitle>
8 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have presented our finite-state, robust parser, PROFER, described some of its workings, and discussed the advantages it may offer for moving towards a tight integration of robust natural language processing with a speech decoder -- those advantages being: its efficiency as an FSM and the possibility that it may provide a useful level of constraint to a recognizer independent of a large, task-specific language model.</Paragraph>
  </Section>
class="xml-element"></Paper>