<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-1103">
  <Title>Context Management with Topics for Spoken Dialogue Systems</Title>
  <Section position="7" start_page="635" end_page="636" type="concl">
    <SectionTitle>
5 Conclusions
</SectionTitle>
    <Paragraph position="0"> The paper has presented a probabilistic topic model to be used as a context model for spoken dialogue systems. The model combines both top-down and bottom-up approaches to topic modelling: the topic tree, which structures domain knowledge, provides expectations of likely topic shifts, whereas the information structure of the utterances is linked to the topic types via topic vectors which describe mutual information between the words and topic types. The Predict-Support Algorithm assigns topics to utterances, and achieves an accuracy rate of 78.68 %, and a precision rate of 74.64%.</Paragraph>
    <Paragraph position="1"> The paper also suggests that the context needed to maintain robustness of spoken dialogue systems can be defined in terms of topic types rather than speech acts. Our model uses actually occurring words and topic information of the domain, and gives highly competitive results for the first ranked topic prediction: there is no need to resort to extra information to disambiguate the three best candidates. Construction of the context, necessary to improve word recognition and for further processing, becomes thus more accurate and reliable.</Paragraph>
    <Paragraph position="2"> Research on statistical topic modelling and combining topic information with spoken language systems is still new and contains several aspects for future research. We have mentioned automatic domain modelling, in which clustering methods can be used to build necessary topic trees. Another research issue is the coverage of topic trees. Topic trees can be generalised in regard to world knowledge, but this requires deep analysis of the utterance meaning, and an inference mechanism to reason on conceptual relations. We will explore possibilities to  extract semantic categories from the parse tree and integrate these with the topic knowledge. We will also investigate further the relation between topics and speech acts, and specify their respective roles in context management for spoken dialogue systems.</Paragraph>
    <Paragraph position="3"> Finally, statistical modelling is prone to sparse data problems, and we need to consider ways to overcome inaccuracies in calculating mutual information.</Paragraph>
  </Section>
class="xml-element"></Paper>