<?xml version="1.0" standalone="yes"?>
<Paper uid="W97-0507">
  <Title>I Using NLP in the design of a conversation aid for non-speaking children</Title>
  <Section position="7" start_page="45" end_page="45" type="concl">
    <SectionTitle>
4 Current research
</SectionTitle>
    <Paragraph position="0"> At present we are carrying out a preliminary investigation of the use of NLP to support the use of PICTALK by children working in structured settings to achieve the following: * Analyse the pragmatic features of children's conversation in a particular setting e.g. a structured news setting.</Paragraph>
    <Paragraph position="1"> * Analyse the variability in the features used by different children in the setting and eventually by the same children in different settings. Try to associate different conversational styles with different utterances for later use in predicting which utterances will be appropriate.</Paragraph>
    <Paragraph position="2"> * Use these analyses to develop a corpus of plausible utterances together with an indication of which features are likely to be most helpful for children with different conversational styles or in different conversational settings.</Paragraph>
    <Paragraph position="3"> * Use the utterance features to predict which utterances will be useful in the chosen setting and to help individual children to select utterances from the corpus to include in PICTALK for use in the setting.</Paragraph>
    <Paragraph position="4"> * Use the analysis to see if there is any scope for the prediction or automatic insertion of utterances during a conversation.</Paragraph>
    <Paragraph position="5"> * Use artificial intelligence to script PICTALK training conversations.</Paragraph>
  </Section>
class="xml-element"></Paper>