University of Cambridge > Talks.cam > NLIP Seminar Series > Applications of Discourse Structure for Spoken Dialogue Systems

Applications of Discourse Structure for Spoken Dialogue Systems

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Johanna Geiss.

Due to the relatively simple structure of the dialogues that occur in the form-filling domains of typical spoken dialogue systems, discourse structure has often seen limited application in such systems. In this research, we investigate whether and how discourse structure can be used to increase the performance of spoken dialogue systems in more complex domains, e.g. tutoring.

In our spoken dialogue research, two types of applications of discourse structure are being pursued: on the system side and on the user side. On the system side, we show how discourse structure can be used to both increase the accuracy of performance prediction, as well as to characterize aspects of user affect and speech recognition problems. On the user side, our results show that presenting a graphical representation of discourse structure increases user satisfaction on a variety of dimensions.

This talk presents joint work with Mihai Rotaru, University of Pittsburgh.

This talk is part of the NLIP Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2017 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity