<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-1219">
  <Title>Smoothing Technniques for Language</Title>
  <Section position="12" start_page="111" end_page="111" type="concl">
    <SectionTitle>
4. Conclusion
</SectionTitle>
    <Paragraph position="0"> In the paper, we have explored various deep knowledge resources such as the name alias phenomenon, the cascaded entity name phenomenon, the use of both a closed dictionary from the training corpus and an open dictionary from the database term list SwissProt and the alias list LocusLink, the abbreviation resolution and in-domain POS using the GENIA corpus.</Paragraph>
    <Paragraph position="1"> In the near future, we will further improve the performance by investigating more on conjunction and disjunction construction and the combination of coreference resolution.</Paragraph>
  </Section>
class="xml-element"></Paper>