<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1604">
  <Title>Detecting Parser Errors Using Web-based Semantic Filters</Title>
  <Section position="6" start_page="33" end_page="33" type="concl">
    <SectionTitle>
4 Conclusions and Future Work
</SectionTitle>
    <Paragraph position="0"> Given a parse of a sentence, WOODWARD constructs a representation that identifies the key semantic relationships implicit in the parse. It then uses a set of Web-based sampling techniques to check whether these relationships are plausible.</Paragraph>
    <Paragraph position="1"> If any of the relationships is highly implausible, WOODWARD concludes that the parse is incorrect.</Paragraph>
    <Paragraph position="2"> WOODWARD successfully detects common errors in the output of the Collins parser including verb arity errors as well as preposition and verb attachment errors. While more extensive experiments are clearly necessary, our results suggest that the paradigm of Web-based semantic filtering could substantially improve the performance of statistical parsers.</Paragraph>
    <Paragraph position="3"> In future work, we hope to further validate this paradigm by constructing additional semantic filters that detect other types of errors. We also plan to use semantic filters such as WOODWARD to build a large-scale corpus of automatically-parsed sentences that has higher accuracy than can be achieved today. Such a corpus could be used to re-train a statistical parser to improve its performance. Beyond that, we plan to embed semantic filtering into the parser itself. If semantic filters become sufficiently accurate, they could rule out enough erroneous parses that the parser is left with just the correct one.</Paragraph>
  </Section>
class="xml-element"></Paper>