Intensional Summaries as Cooperative Responses in Dialogue: Automation and Evaluation
Polifroni, Joseph and Walker, Marilyn

Article Structure

Abstract

Despite its long history, and a great deal of research producing many useful algorithms and observations, research in cooperative response generation has had little impact on the recent commercialization of dialogue technologies, particularly within the spoken dialogue community.

Introduction

Research in cooperative response generation has had a long history and produced many useful algorithms and observations (Mays 1980; Pollack et al.1982; Joshi et al., 1986; Kalita et al., 1986) inter alia.

Intensional Summaries

This section describes algorithms which result in the four types of intensional summaries shown in Fig.

Experiment One

This experiment asks whether subjects prefer intensional summaries to a baseline system-initiative strategy.

Experiment Two

The first experiment shows that users prefer intensional summaries; the purpose of the second experiment is to investigate what makes a good intensional summary.

Conclusion

We first compared intensional summary cooperative responses against a system initiative dialogue strategy in CRUISER.

Topics

feature sets

Appears in 6 sentences as: Feature Sets (1) feature sets (5)
In Intensional Summaries as Cooperative Responses in Dialogue: Automation and Evaluation
  1. We derive two types of feature sets from the responses: features derived from each user model and features derived from attributes of the query/ response pair itself.
    Page 7, “Experiment Two”
  2. The five feature sets for the user model are:
    Page 7, “Experiment Two”
  3. 0 allUtz’lz’ty: 12 features consisting of the high, low, and average utility scores from the previous three feature sets .
    Page 7, “Experiment Two”
  4. Three feature sets are derived from the query and response pair:
    Page 7, “Experiment Two”
  5. Sys l Feature Sets | Acc(%) l
    Page 7, “Experiment Two”
  6. Table 3: Accuracy of feature sets for predicting preferred summary type.
    Page 7, “Experiment Two”

See all papers in Proc. ACL 2008 that mention feature sets.

See all papers in Proc. ACL that mention feature sets.

Back to top.