<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-1201">
  <Title>Recognizing Names in Biomedical Texts using Hidden Markov Model and SVM plus Sigmoid</Title>
  <Section position="15" start_page="11" end_page="11" type="concl">
    <SectionTitle>
7. CONCLUSION
</SectionTitle>
    <Paragraph position="0"> In the paper, we describe our HMM-based named entity recognition system in the biomedical domain, named PowerBioNE. Various lexical, morphological, syntactic, semantic and discourse features are incorporated to cope with the special phenomena in biomedical named entity recognition.</Paragraph>
    <Paragraph position="1"> In addition, a SVM plus sigmoid is proposed to effectively resolve the data sparseness problem.</Paragraph>
    <Paragraph position="2"> Finally, we present two post-processing modules to deal with cascaded entity name and abbreviation phenomena.</Paragraph>
    <Paragraph position="3"> The main contributions of our work are the novel name alias feature in the biomedical domain, the SVM plus sigmoid approach in the effective resolution of the data sparseness problem in our system and its integration with the Hidden Markov Model.</Paragraph>
    <Paragraph position="4"> In the near future, we will further improve the performance by investigating more on conjunction and disjunction construction, the synonym phenomenon, and exploration of extra resources (e.g. dictionary).</Paragraph>
  </Section>
class="xml-element"></Paper>