<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1140">
  <Title>High-Performance Tagging on Medical Texts</Title>
  <Section position="8" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> We collected experimental evidence, contrary to recent claims (Campbell and Johnson, 2001), that off-the-shelf NLP tools can be applied to MLP in a straightforward way. We explain this finding with statistically significant POS n-gram type overlaps of newspaper language and medical sublanguage, which has not been recognized before.</Paragraph>
    <Paragraph position="1"> To the best of our knowledge, this is the first tagging study that reaches a 98% accuracy level for a data-driven tagger (which must be distinguished from linguistically backuped taggers which come with 'heavy' parsing machinery (Samuelsson and Voutilainen, 1997)). Still, we deal with a specialized sublanguage simpler in structure compared with newspaper language, although we kept it diverse through the various text genres.</Paragraph>
    <Paragraph position="2"> Acknowledgements. We would like to thank our students, Inka Benthin, Lucas Champollion and Caspar Hasenclever, for their excellent work as human taggers. This work was partly supported by DFG grant KL 640/5-1.</Paragraph>
  </Section>
class="xml-element"></Paper>