<?xml version="1.0" standalone="yes"?>
<Paper uid="W03-1715">
  <Title>Abductive Explanation-based Learning Improves Parsing Accuracy and Efficiency</Title>
  <Section position="5" start_page="0" end_page="0" type="concl">
    <SectionTitle>
4 Conclusions
</SectionTitle>
    <Paragraph position="0"> Explanation-based Learning has been used to speed-up natural language parsing. We show that the loss in accuracy results from the deductive basis of parsers, not the EBL framework. D-EBL does not extend the deductive closure and acquires only empirical (disambiguation) knowledge. The accuracy declines due to cached errors, the statistical bias the filters introduce and the usage of shortcuts with limited contextual information.</Paragraph>
    <Paragraph position="1"> Alternatively, if the parser uses abduction, the deductive closure of the parser enlarges. This makes accuracy improvements possible - not a logical consequence. In practice, the extended deductive closure compensates for negative factors such as wrong parses or unbalanced distributions in the cache.</Paragraph>
    <Paragraph position="2"> On a more abstract level, the paper treats the problem of automatic knowledge acquisition for Chinese NLP. Theory and practice show that abduction-based NLP applications acquire new knowledge and increase accuracy and speed. Future research will maximize the gains.</Paragraph>
  </Section>
class="xml-element"></Paper>