<?xml version="1.0" standalone="yes"?>
<Paper uid="W02-0306">
  <Title>A Transformational-based Learner for Dependency Grammars in Discharge Summaries</Title>
  <Section position="7" start_page="2" end_page="2" type="evalu">
    <SectionTitle>
6 Results
</SectionTitle>
    <Paragraph position="0"> The three template sets generated three rule sets, each of which was evaluated on the 170 sentence test set. Each template set was trained with increasing amounts of the training corpus to measure the effect of the training set size on the learner's accuracy. Chart 1 shows the improvement in accuracy gained through larger training sets. The best dependency accuracy and number of rules generated for each template set is reported in table 1.</Paragraph>
    <Paragraph position="1">  To measure the effect of sentence length on parsing accuracy, the best parser rules were retested on two subsets of the test sets. The first subset contained sentences with a length less than ten words and the second contained sentences of length less than twenty. The resulting accuracy of the parser on these sentences is summarized in table 2. The top ten rules acquired with the third template set are reported in table 3.</Paragraph>
  </Section>
class="xml-element"></Paper>