<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-1524">
  <Title>Vancouver, October 2005. c(c)2005 Association for Computational Linguistics TFLEX: Speeding up Deep Parsing with Strategic Pruning</Title>
  <Section position="5" start_page="194" end_page="194" type="concl">
    <SectionTitle>
4 Conclusions
</SectionTitle>
    <Paragraph position="0"> In this paper, we described a combination of ef cient parsing techniques to improve parsing speed and coverage with the TRIPS deep parsing grammar.</Paragraph>
    <Paragraph position="1">  parse depending on (aggregated) sentence lengths. 5 denotes sentences with 5 or fewer words, 25 sentences with more than 20 words.</Paragraph>
    <Paragraph position="2"> The TFLEX system uses an all-paths left-corner parsing from the LCFLEX parser, made tractable by a pruning algorithm based on ambiguity packing and local features, generalizable to other uni cation grammars. Our pruning algorithm provides a better ef ciency-coverage balance than best- rst parsing with chart limits as utilised by the TRIPS parser.</Paragraph>
  </Section>
class="xml-element"></Paper>