Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Empirical Evaluation of a Reinforcement Learning Spoken Dialogue System
Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
The Journal of Machine Learning Research
Pattern Recognition and Machine Learning (Information Science and Statistics)
Pattern Recognition and Machine Learning (Information Science and Statistics)
Automatic learning of dialogue strategy using dialogue simulation and reinforcement learning
HLT '02 Proceedings of the second international conference on Human Language Technology Research
Evaluating user simulations with the Cramér-von Mises divergence
Speech Communication
Data-driven user simulation for automated evaluation of spoken dialog systems
Computer Speech and Language
Agenda-based user simulation for bootstrapping a POMDP dialogue system
NAACL-Short '07 Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers
SIGDIAL '09 Proceedings of the SIGDIAL 2009 Conference: The 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue
SIGDIAL '09 Proceedings of the SIGDIAL 2009 Conference: The 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Parameter estimation for agenda-based user simulation
SIGDIAL '10 Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology (TIST)
| Hi-index | 0.00 |
User simulation is frequently used to train statistical dialog managers for task-oriented domains. At present, goal-driven simulators (those that have a persistent notion of what they wish to achieve in the dialog) require some task-specific engineering, making them impossible to evaluate intrinsically. Instead, they have been evaluated extrinsically by means of the dialog managers they are intended to train, leading to circularity of argument. In this paper, we propose the first fully generative goal-driven simulator that is fully induced from data, without hand-crafting or goal annotation. Our goals are latent, and take the form of topics in a topic model, clustering together semantically equivalent and phonetically confusable strings, implicitly modelling synonymy and speech recognition noise. We evaluate on two standard dialog resources, the Communicator and Let's Go datasets, and demonstrate that our model has substantially better fit to held out data than competing approaches. We also show that features derived from our model allow significantly greater improvement over a baseline at distinguishing real from randomly permuted dialogs.