Predicting user evaluations of spoken dialog systems using semi-supervised learning
Refereed conference paper presented and published in conference proceedings

Times Cited
Altmetrics Information

Other information
AbstractUser evaluations of dialogs from a spoken dialog system (SDS) can be directly used to gauge the system's performance. However, it is costly to obtain manual evaluations of a large corpus of dialogs. Semi-supervised learning (SSL) provides a possible solution. This process learns from a small amount of manually labeled data, together with a large amount of unlabeled data, and can later be used to perform automatic labeling. We conduct comparative experiments among SSL approaches, classical regression and supervised learning in evaluation of dialogs from CMU's Let's Go Bus Information System. Two typical SSL methods, namely co-training and semi-supervised support vector machine (S3VM), are found to outperform the other approaches in automatically predicting user evaluations of unseen dialogs in the case of low training rate. ©2010 IEEE.
All Author(s) ListLi B., Yang Z., Zhu Y., Meng H., Levow G., King I.
Name of Conference2010 IEEE Workshop on Spoken Language Technology, SLT 2010
Start Date of Conference12/12/2010
End Date of Conference15/12/2010
Place of ConferenceBerkeley, CA
Country/Region of ConferenceUnited States of America
Detailed descriptionorganized by IEEE,
Pages283 - 288
LanguagesEnglish-United Kingdom
KeywordsEvaluation, Semi-Supervised learning, Spoken dialog system

Last updated on 2021-01-03 at 00:48