<?xml version="1.0" standalone="yes"?>
<Paper uid="P02-1006">
  <Title>Learning Surface Text Patterns for a Question Answering System</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> The web results easily outperform the TREC results. This suggests that there is a need to integrate the outputs of the Web and the TREC corpus. Since the output from the Web contains many correct answers among the top ones, a simple word count could help in eliminating many unlikely answers. Thi s would work well for question types like BIRTHDATE or LOCATION but is not clear for question types like DEFINITION.</Paragraph>
    <Paragraph position="1"> The simplicity of this method makes it perfect for multilingual QA. Many tools required by sophisticated QA systems (named entity taggers, parsers, ontologies, etc.) are language specific and require significant effort to adapt to a new language. Since the answer patterns used in this method are learned using only a small number of manual training terms, one can rapidly learn patterns for n ew languages, assuming the web search engine is appropriately switched.</Paragraph>
  </Section>
class="xml-element"></Paper>