<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-1051">
  <Title>Error Driven Word Sense Disambiguation</Title>
  <Section position="9" start_page="323" end_page="323" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> We presented a WSD system with reasonable results as well as suggestions for improving it.</Paragraph>
    <Paragraph position="1"> We will implement these improvements in the context of the SENSEVAL experiment and we plan to extend the system to other languages, with special attention to French and Italian. 6 Indeed, the availability of lexical resources providing a word sense classification with roughly the same granularity of the 45 top classes of Wordnet makes our method applicable also to languages for which no sense tagged corpora has been produced. In the long run, these extensions will lead, we hope, to better systems for foreign language understanding and machine translation.</Paragraph>
    <Paragraph position="2"> Acknowledgements We are grateful to Ken Beesley, Andrea Bolioli, Gregory Grefenstette, 6The system will be used in the MIETTA project (LE4-8343) for enhancing the performance of the information extraction and information retrieval module. David Hull, Hinrich Schuetze and Annie Zaenen for their comments and discussion on earlier versions of this paper. Our gratitude also goes to Vincent Nainemoutou and Herve Poirier for providing us with technical support. Any remaining errors are our own fault.</Paragraph>
  </Section>
class="xml-element"></Paper>