<?xml version="1.0" standalone="yes"?>
<Paper uid="H01-1036">
  <Title>Information Extraction with Term Frequenciesa0</Title>
  <Section position="5" start_page="0" end_page="0" type="concl">
    <SectionTitle>
5. CONCLUSION
</SectionTitle>
    <Paragraph position="0"> Overall, the information extraction component improves the question answering system. Notably, the term frequency algorithm does not require information regarding the structure or grammar of a natural language; therefore the algorithm may be use in many natural languages. The term frequency algorithm can even extract answers when the question's meaning is completely unknown. Having an elementary and reliable way to evaluate each term in a set of passages is useful. One possibility is to add highly weighted terms to the original query.</Paragraph>
    <Paragraph position="1"> In theory, as the corpus size expands, the performance of the system should increase as more duplicate information will become available. Finally, the initial value of the term frequency algorithm is beneficial to the overall system and future applications of question answering.</Paragraph>
  </Section>
class="xml-element"></Paper>