<?xml version="1.0" standalone="yes"?>
<Paper uid="W97-0506">
  <Title>Augmented and alternative NLP techniques for augmentative and alternative communication</Title>
  <Section position="5" start_page="41" end_page="41" type="concl">
    <SectionTitle>
4 Conclusions and future work
</SectionTitle>
    <Paragraph position="0"> We have described a prediction system which can adapt to a user's vocabulary and syntax with fairly small amounts of data. The techniques described are all ones which can be used on the fly, although for efficiency it might be desirable todo morphological analysis and n-gram frequency at times when the system is not being actively used (e.g. overnight).</Paragraph>
    <Paragraph position="1"> We have discussed the limitations of the e~ciency of prediction, and introduced the idea of cogeneration which combines free text entry with fixed text associated with templates.</Paragraph>
    <Paragraph position="2"> Our prediction work has proven practical utility since our user selects predictions at close to the maximal level (i.e., it is rare for a predicted possibility to be missed). It is difficult to determine bow much saving in utterance generation time results from prediction, but it is clear that it considerably reduces physical effort. Our user will not accept any system which does not incorporate prediction. In contrast, our work on cogeneration is at a very early stage. We aim to build the cogeneration system in a modular fashion that allows the reuse of knowledge sources. For example, we expect the semantic categories described in the previous section to be useful in prediction outside the context of a full cogeneration system and also to allow better output from the speech synthesizer, e.g., in the pronunciation of homographs, such as bow, in stress placement for compounds etc. We believe that such flexibility is necessary to maximize the chances of NLP research having practical utility for AAC systems.</Paragraph>
  </Section>
class="xml-element"></Paper>