<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-1005">
  <Title>Learning Semantic Classes for Word Sense Disambiguation</Title>
  <Section position="6" start_page="39" end_page="40" type="concl">
    <SectionTitle>
5 Conclusion and Future Work
</SectionTitle>
    <Paragraph position="0"> We analyzed the problem of Knowledge Acquisition Bottleneck in WSD, proposed using a general set of semantic classes as a trade-off, and discussed why such a system is promising. Our formulation allowed us to use training examples from words different from the actual word being classified. This makes the available labelled data reusable for different words, relieving the above problem. In order to facilitate learning, we introduced a technique based on word sense similarity.</Paragraph>
    <Paragraph position="1"> The generic classes we learned can be mapped to  finer grained senses with simple heuristics. Through empirical findings, we showed that our system can attain state of the art performance, when applied to standard fine-grained WSD evaluation tasks.</Paragraph>
    <Paragraph position="2"> In the future, we hope to improve on these results: Instead of using WORDNET unique beginners, using more natural semantic classes based on word usage would possibly improve the accuracy, and finding such classes would be a worthwhile area of research. As seen from our results, selecting correct similarity measure has an impact on the final outcome. We hope to work on similarity measures that are more applicable in our task.</Paragraph>
  </Section>
class="xml-element"></Paper>