<?xml version="1.0" standalone="yes"?>
<Paper uid="N06-2036">
  <Title>Word Domain Disambiguation via Word Sense Disambiguation</Title>
  <Section position="5" start_page="142" end_page="143" type="concl">
    <SectionTitle>
5 Conclusions and Further Work
</SectionTitle>
    <Paragraph position="0"> Current approaches to WDD have assumed that special purpose algorithms are needed to model the WDD task. We have shown that very competitive and perhaps unrivaled results (pending on evaluation of our WDD algorithm with the DSO corpus) can be obtained using WSD as the basis for subject domain assignment. This improvement in WDD performance can be used to  obtain further gains in WSD accuracy, following Wilks and Stevenson (1998), Magnini et al.</Paragraph>
    <Paragraph position="1"> (2001) and Gliozzo et al. (2004). A more accurate WSD model will in turn yield yet better WDD results, as demonstrated in this paper.</Paragraph>
    <Paragraph position="2"> Consequently, further improvements in accuracy for both WSD and WDD can be expected through a bootstrapping cycle where WDD results are fed as input to the WSD process, and the resulting improved WSD model is then used to achieve better WDD results. We intend to explore this possibility in future extensions of this work.</Paragraph>
  </Section>
class="xml-element"></Paper>