<?xml version="1.0" standalone="yes"?>
<Paper uid="I05-2030">
  <Title>Opinion Extraction Using a Learning-Based Anaphora Resolution Technique</Title>
  <Section position="7" start_page="177" end_page="177" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper, we have proposed a machine learning-based method for the extraction of opinions on consumer products by reducing the problem to that of extracting attribute-value pairs from texts. We have pointed out the similarity between the tasks of anaphora resolution and opinion extraction, and have applied the machine learning-based method designed for anaphora resolution to opinion extraction. The experimental results reported in this paper show that identifying the corresponding attribute for a given value expression is effective in both pairedness determination and opinionhood determination.</Paragraph>
  </Section>
class="xml-element"></Paper>