<?xml version="1.0" standalone="yes"?>
<Paper uid="W01-1602">
  <Title>VariantTransduction: A Method for Rapid Developmentof InteractiveSpoken Interfaces</Title>
  <Section position="9" start_page="0" end_page="0" type="concl">
    <SectionTitle>
8 Concluding remarks
</SectionTitle>
    <Paragraph position="0"> Wehave described an approach to constructing interactivespoken interfaces. The approach is aimed at shifting the burden of handling linguistic variation for new applications from the application developer (or data collection lab)totheunderlying spokenlanguage understanding technology itself. Applications are specied in terms of a relatively small number of examples, while the mapping between the inputs that users speak, variants of the examples, and application actions, are handled by the system. In this approach, we avoid the use of intermediate semantic representations, making it possible to develop general approaches to linguistic variation and dialog responses in terms of word-string to word-string transformations. Conrmation requests used in the dialog are computed automatically fromvariants in awayintended to minimize misleading the user about the application actions to be executed by the system. The quantitative results we have presented indicate that a surprisingly small number of training examples can provide useful performance in a call routing application. These results suggest that, even at its current early stage of development, the variant transduction approach is a viable option for constructing spoken language applications rapidly without specialized expertise. This may be appropriate, for example, for bootstrapping data collection, as well as for situations (e.g. small businesses) for whichdevelopment of a full-blown system would be too costly. When a full dataset is available, the method can provide similar performance to currenttechniques while reducing the level of skill necessary to build new applications.</Paragraph>
  </Section>
class="xml-element"></Paper>