<?xml version="1.0" standalone="yes"?>
<Paper uid="W02-0806">
  <Title>Assessing System Agreement and Instance Difficulty in the Lexical Sample Tasks of SENSEVAL-2</Title>
  <Section position="6" start_page="0" end_page="0" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> This paper presents an analysis of the results from the English and Spanish lexical sample tasks of SENSEVAL-2. The analysis is based on the kappa statistic and a measure known as optimal combination. It also assesses the difficulty of the test instances in these lexical samples. We find that there are a significant number of test instances that were not disambiguated correctly by any system, and that there is some correlation between instance difficulty and the number of available training examples.</Paragraph>
  </Section>
class="xml-element"></Paper>