Quantitative and qualitative evaluation of Darpa Communicator spoken dialogue systems
ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
Developing a flexible spoken dialog system using simulation
ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Evaluating information presentation strategies for spoken recommendations
Proceedings of the 2007 ACM conference on Recommender systems
Hybrid reinforcement/supervised learning of dialogue policies from fixed data sets
Computational Linguistics
EACL '06 Proceedings of the Eleventh Conference of the European Chapter of the Association for Computational Linguistics: Posters & Demonstrations
An empirical study of the influence of user tailoring on evaluative argument effectiveness
IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 2
Computer Speech and Language
Modeling spoken decision support dialogue and optimization of its dialogue strategy
ACM Transactions on Speech and Language Processing (TSLP)
A strategy for information presentation in spoken dialog systems
Computational Linguistics
International Journal of Mobile Human Computer Interaction
| Hi-index | 0.00 |
Recent work on information presentation in dialogue systems combines user modelling (UM) and stepwise refinement through clustering and summarisation (SR) in the UMSR approach. An evaluation in which participants rated dialogue transcripts showed that UMSR presents complex trade-offs understandably, provides users with a good overview of their options, and increases users' confidence that all relevant options have been presented (Demberg and Moore, 2006). In this paper, we evaluate the effectiveness of the UMSR approach in a more realistic setting, by incorporating this information presentation technique into a full end-to-end dialogue system in the city information domain, and comparing it with the traditional approach of presenting information sequentially. Our results suggest that despite complications associated with a real dialogue system setting, the UMSR model retains its advantages.