<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-1103">
  <Title>Context Management with Topics for Spoken Dialogue Systems</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> One of the fragile points in integrated spoken language systems is the erroneous analyses of the initial speech input. 1 The output of a speech recognizer has direct influence on the performance of other modules of the system (dealing with dialogue management, translation, database search, response planning, etc.), and the initial inaccuracy usually gets accumulated in the later stages of processing. Performance of speech recognizers can be improved by tuning their language model and lexicon, but problems still remain with the erroneous ranking of the best paths: information content of the selected utterances may be wrong. It is thus essential to use contextual information to compensate various errors in the output, to provide expectations of what will be said next and to help to determine the appropriate dialogue state.</Paragraph>
    <Paragraph position="1"> However, negative effects of an inaccurate context have also been noted: cumulative error in discourse context drags performance of the system below the rates it would achieve were contextual information 1 Alexandersson (1996) remarks that with a 3000 word lexicon, a 75 % word accuracy means that in practice the word lattice does not contain the actually spoken sentence, not used (Qu et al., 1996; Church and Gale, 1991).</Paragraph>
    <Paragraph position="2"> Successful use of context thus presupposes appropriate context management: (1) features that define the context are relevant for the processing task, and (2) construction of the context is accurate.</Paragraph>
    <Paragraph position="3"> In this paper we argue in favour of using one type of contextual information, topic information, to maintain robustness of a spoken language system. Our model deals with the information content of utterances, and defines the context in terms of topic types, related to the current domain knowledge and represented in the form of a topic tree.</Paragraph>
    <Paragraph position="4"> To update the context with topics we introduce the Predict-Support algorithm which selects utterance topics on the basis of topic transitions described in the topic tree and words recognized in the current utterance. At present, the algorithm is designed as a filter which re-orders the candidates produced by the speech recognizer, but future work encompasses integration of the algorithm into a language model and actual speech recognition process.</Paragraph>
    <Paragraph position="5"> The paper is organised as follows. Section 2 reviews the related previous research and sets out our starting point. Section 3 presents the topic model and the Predict-Support algorithm, and section 4 gives results of the experiments conducted with the model. Finally, section 5 summarises the properties of the topic model, and points to future research.</Paragraph>
  </Section>
class="xml-element"></Paper>