<?xml version="1.0" standalone="yes"?>
<Paper uid="W97-0808">
  <Title>Word Sense Disambiguation for Acquisition of Selectional Preferences</Title>
  <Section position="9" start_page="68" end_page="68" type="ackno">
    <SectionTitle>
5 Future
</SectionTitle>
    <Paragraph position="0"> The importance of word sense disambiguation on the input data needs to be subjected to formal evaluation. null Undoubtedly different underlying semantic roles will occur in a specified argument slot and this will confuse the issue. It would be interesting to examine the preferences acquired where the data used is specific to the subca.tegorisation frame as well as to the argument slot. Naturally this cart only be done if we have sufficient data to start with.</Paragraph>
    <Paragraph position="1"> Where there is insufficient data for a target verb it may be worth merging the data for similar verbs.</Paragraph>
    <Paragraph position="2"> The WordNet verb hierarchies might provide a useful classification for this purpose.</Paragraph>
    <Paragraph position="3"> Although WordNet is used here, the classification could easily be changed. It would be interesting to compare results from a re-implementation using an alternative hierarchy more in tune with the corpus data. The hierarchy could be produced by humans or automatically.</Paragraph>
    <Paragraph position="4"> The encoding of the model and data for the MDL principle needs attention as this will affect the level of generalisation. As yet the description length has assumed a tree rather than a DAG and it is apparent that cuts at nodes with shared daughters will be penalised in the current scheme.</Paragraph>
  </Section>
class="xml-element"></Paper>