<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-3502">
  <Title>Backbone Extraction and Pruning for Speeding Up a Deep Parser for Dialogue Systems</Title>
  <Section position="7" start_page="14" end_page="15" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> We described a combination of ef cient parsing techniques to improve parsing speed and coverage with the TRIPS deep parsing grammar. We showed that context-free parsing was inef cient on a backbone extracted from an existing uni cation grammar, and demonstrated how to make all-path parsing more tractable by a new pruning algorithm based  on ambiguity packing and local features, generalisable to other uni cation grammars. We demonstrated that our pruning algorithm provides better ef ciency-coverage balance than the best- rst parsing with chart limits utilised by the TRIPS parser, and discussed the design implications for other robust parsing grammars.</Paragraph>
  </Section>
class="xml-element"></Paper>