<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-1033">
  <Title>Flexible Guidance Generation using User Model in Spoken Dialogue Systems</Title>
  <Section position="7" start_page="1" end_page="1" type="concl">
    <SectionTitle>
5 Conclusions
</SectionTitle>
    <Paragraph position="0"> We have proposed and evaluated user models for generating cooperative responses adaptively to individual users. The proposed user models consist of the three dimensions: skill level to the system, knowledge level on the target domain and the degree of hastiness. The user models are identified using features specific to spoken dialogue systems as well as semantic attributes. They are automatically derived by decision tree learning, and all features used for skill level and hastiness are independent of domain-specific knowledge. So, it is expected that the derived user models can be used in other domains generally.</Paragraph>
    <Paragraph position="1"> The experimental evaluation with 20 novice users shows that the skill level of novice users was improved more rapidly by incorporating the user models, and accordingly the dialogue duration becomes shorter more immediately. The result is achieved by the generated cooperative responses based on the proposed user models. The proposed user models also suppress the redundancy by changing the dialogue procedure and selecting contents of responses. Thus, they realize user-adaptive dialogue strategies, in which the generated cooperative responses serve as good guidance for novice users without increasing the dialogue duration for skilled users.</Paragraph>
  </Section>
class="xml-element"></Paper>