<?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="3" start_page="9" end_page="9" type="intro">
    <SectionTitle>
2 Motivation
</SectionTitle>
    <Paragraph position="0"> The work reported in this paper was done as part of the process of developing a dialogue system that incorporates deep natural language understanding.</Paragraph>
    <Paragraph position="1"> We needed a grammar that provides lexical semantic interpretation, supports parsing fragmentary utterance in dialogue, and could be used to start development without large quantities of corpus data.</Paragraph>
    <Paragraph position="2"> TRIPS ful lled our requirements better than similar alternatives, such as LINGO ERG (Copestake and Flickinger, 2000) or XLE (Maxwell and Kaplan, 1994).</Paragraph>
    <Paragraph position="3"> TRIPS produces logical forms which include semantic classes and roles in a domain-independent frame-based formalism derived from FrameNet and VerbNet (Dzikovska et al., 2004; Kipper et al., 2000). Lexical semantic features are known to be helpful in both deep (Tetreault, 2005) and shallow interpretation tasks (Narayanan and Harabagiu, 2004). Apart from TRIPS, these have not been integrated into existing deep grammars. While both LINGO-ERG and XLE include semantic features related to scoping, in our applications the availability of semantic classes and semantic role assignments was more important to interpretation, and these features are not currently available from those parsers. Finally, TRIPS provides a domain-independent parse selection model, as well as rules for interpreting discourse fragments (as was also done in HPSG (Schlangen and Lascarides, 2003), a feature actively used in interpretation.</Paragraph>
    <Paragraph position="4"> While TRIPS provides the capabilities we need, its parse times for long sentences (above 15 words long) are intolerably long. We considered two possible techniques for speeding up parsing: speeding up uni cation using the techniques similar to the LINGO system (Copestake and Flickinger, 2000), or using backbone extraction (Maxwell and Kaplan, 1994; Ros*e and Lavie, 2001; Briscoe and Carroll, 1994). TRIPS already uses a fast uni cation algorithm similar to quasi-destructive uni cation, avoiding copying during uni cation.1 However, the TRIPS grammar retains the notion of phrase structure, and thus it was more natural to chose to use backbone extraction with ambiguity packing to speed up the parsing.</Paragraph>
    <Paragraph position="5"> As a foundation for our optimisation work, we started with the freely available LCFLEX parser (Ros*e and Lavie, 2001). LCFLEX is an all-paths parser that uses left-corner prediction and ambiguity packing to make all-paths parsing tractable, and which was shown to be ef cient for long sentences with somewhat less complex uni cation augmented context-free grammars. We show that all-paths parsing with LCFLEX is not tractable for the ambiguity level in the TRIPS grammar, but that by introducing a pruning method that uses ambiguity packing to guide pruning decisions, we can achieve signi cant improvements in both speed and coverage compared to the original TRIPS parser.</Paragraph>
  </Section>
class="xml-element"></Paper>