<?xml version="1.0" standalone="yes"?>
<Paper uid="W02-0302">
  <Title>Tagging Gene and Protein Names in Full Text Articles</Title>
  <Section position="5" start_page="0" end_page="10" type="concl">
    <SectionTitle>
4 Conclusion
</SectionTitle>
    <Paragraph position="0"> We conclude that an information extraction system to tag gene and protein names in Medline abstracts (ABGene) can be applied to full text articles in the biomedical domain. We  have shown how modifications to the processing (applying a sentence score threshold, and using a large pool of putative gene/protein names) can affect the system's performance. We are currently exploring methods to filter the 2.16 million putative gene/protein names extracted from Medline using our system. The resulting set of gene/protein names, a significant addition to the 42K names available from the Gene Ontology Consortium and LocusLink, will be used to improve the performance of text processing on full text articles in the biomedical domain.</Paragraph>
  </Section>
class="xml-element"></Paper>