Abstract
Recent work on evaluation of spoken dialogue systems suggests that the information presentation phase of complex dialogues is often the primary contributor to dialogue duration. This indicates that better algorithms are needed for the presentation of complex information in speech. Currently however we lack data about the tasks and dialogue strategies on which to base such algorithms. In this paper, we describe a Wizard of Oz tool and a study which applies user models based on multi-attribute decision theory to the problem of generating tailored and concise system responses for a spoken dialogue system. The resulting Wizard corpus will be distributed by the LDC as part of our work on the ISLE project.
Original language | English |
---|---|
Title of host publication | Proceedings of the Third International Conference on Language Resources and Evaluation, LREC 2002, May 29-31, 2002, Las Palmas, Canary Islands, Spain. |
Publisher | European Language Resources Association (ELRA) |
Number of pages | 8 |
Publication status | Published - 2002 |