<?xml version="1.0" standalone="yes"?>
<Paper uid="N03-1012">
  <Title>Semantic Coherence Scoring Using an Ontology</Title>
  <Section position="8" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Concluding Remarks
</SectionTitle>
    <Paragraph position="0"> The ONTOSCORE system described herein automatically performs ontology-based scoring of sets of concepts con- null word/concept relation stituting an adequate representation of speech recognition hypotheses. To date, the algorithm has been implemented in a software which is employed by a multi-domain and multi-modal dialogue system and applied to the task of scoring n-best lists of SRH, thus producing a score expressing how well a given SRH fits within the domain model. For this task, it provides an alternative knowledge-based score next to the ones provided by the ASR and the NLU system. In the evaluation of our system we employed an ontology that was not designed for this task, but already existed as the system's internal knowledge representation.</Paragraph>
    <Paragraph position="1"> As future work we will examine how the computation of a discourse dependent semantic coherence score, i.e. how well a given SRH fits within domain model with respect to the previous discourse, can improve the overall score. Additionally, we intend to calculate the semantic coherence score with respect to individual domains of the system, thus enabling domain recognition and domain change detection in complex multi-modal and multi-domain spoken dialogue systems. Currently, we are also beginning to investigate whether the proposed method can be applied to scoring sets of potential candidates for resolving the semantic interpretation of ambiguous, polysemous and metonymic language use.</Paragraph>
  </Section>
class="xml-element"></Paper>