<?xml version="1.0" standalone="yes"?>
<Paper uid="A88-1009">
  <Title>RESPONDING TO SEMANTICALLY ILL-FORMED INPUT</Title>
  <Section position="8" start_page="67" end_page="69" type="concl">
    <SectionTitle>
7. Assessment
</SectionTitle>
    <Paragraph position="0"> These results, while not definitive, suggest that the technique described above /s a useful one, but will have to be combined with other techniques to forge a general strategy for dealing with problems encountered in interpreting the input.</Paragraph>
    <Paragraph position="1"> Extending the syntactic coverage of our system, which at present is quite limited, should reduce the frequency of some types of failure. To obtain further improvement, we will have to extend our technique to deal with input containing unknown words. It should be possible to do this in a straightforward way by adding dictionary entries for the closed syntactic classes, guessing from morphological clues the syntactic class(es) of new words not in the dictionary, obtaining a parse, and then applying the techniques just described (with a new word treated as a semantic unknown, not belonging to any class).</Paragraph>
    <Paragraph position="2"> Our system only offers suggestions; it does not aspire to correct the user's input. That would be an unreasonable expectation for our simple system, which does not maintain any user or discourse model. Our current system typically generates several equally-rated suggestions for an ill-formed input. For a more sophisticated system  which does maintain a richer model, correction may be a feasible goal. Specifically, we might generate the suggested questions as we do now and then see if any question corresponds to a plausible goal.</Paragraph>
  </Section>
class="xml-element"></Paper>