<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-0825">
  <Title>Contextual Semantics for WSD</Title>
  <Section position="5" start_page="0" end_page="0" type="evalu">
    <SectionTitle>
4 Results and conclusion
</SectionTitle>
    <Paragraph position="0"> For the third edition of the Senseval campaign, the sense repository for the verbs was different, using WordsMyth instead of WordNet. The proportion of nouns, verbs and adjectives was also different. Because of these changes, it is difficult to compare this evaluation results with the previous ones.</Paragraph>
    <Paragraph position="1">  fine grain scores, while the column named Coarse is for the coarse grained senses.</Paragraph>
    <Paragraph position="2"> Although we are using different strategies, both systems give approximately the same results for fine grained precision. According to the previous evaluation, we can observe almost 5% increase in precision. However, this increase cannot be taken as significant because of the differences between the evaluations.</Paragraph>
    <Paragraph position="3"> A comparative evaluation have to be carried now in order to establish if a combination of both system could improve the final score.</Paragraph>
  </Section>
class="xml-element"></Paper>