<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0602">
  <Title>A Statistical Semantic Parser that Integrates Syntax and Semantics</Title>
  <Section position="12" start_page="15" end_page="15" type="concl">
    <SectionTitle>
8 Conclusion
</SectionTitle>
    <Paragraph position="0"> SCISSOR learns statistical parsers that integrate syntax and semantics in order to produce a semantically augmented parse tree that is then used to compositionally generate a formal meaning representation. Experimental results in two domains, a natural-language database interface and an interpreter for coaching instructions in robotic soccer, have demonstrated that SCISSOR generally produces more accurate semantic representations than several previous approaches. By augmenting a state-of-the-art statistical parsing model to include semantic information, it is able to integrate syntactic and semantic clues to produce a robust interpretation that supports the generation of complete formal meaning representations. null</Paragraph>
  </Section>
class="xml-element"></Paper>