Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Separating Skills from Preference: Using Learning to Program by Reward
ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Trainable sentence planning for complex information presentation in spoken dialog systems
ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Natural language generation as planning under uncertainty for spoken dialogue systems
EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
What game theory can do for NLG: the case of vague language
ENLG '09 Proceedings of the 12th European Workshop on Natural Language Generation
The Hidden Information State model: A practical framework for POMDP-based spoken dialogue management
Computer Speech and Language
Learning contrastive connectives in sentence realization ranking
SIGdial '08 Proceedings of the 9th SIGdial Workshop on Discourse and Dialogue
Individual and domain adaptation in sentence planning for dialogue
Journal of Artificial Intelligence Research
Optimising information presentation for spoken dialogue systems
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Adaptive referring expression generation in spoken dialogue systems: evaluation with real users
SIGDIAL '10 Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
Spoken Dialog Challenge 2010: comparison of live and control test results
SIGDIAL '11 Proceedings of the SIGDIAL 2011 Conference
Optimising natural language generation decision making for situated dialogue
SIGDIAL '11 Proceedings of the SIGDIAL 2011 Conference
SIGDIAL '11 Proceedings of the SIGDIAL 2011 Conference
Optimising incremental dialogue decisions using information density for interactive systems
EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
Ghost-in-the-machine: initial results
Proceedings of the 2014 ACM/IEEE international conference on Human-robot interaction
The listening talker: A review of human and algorithmic context-induced modifications of speech
Computer Speech and Language
| Hi-index | 0.00 |
We present evaluation results with human subjects for a novel data-driven approach to Natural Language Generation in spoken dialogue systems. We evaluate a trained Information Presentation (IP) strategy in a deployed tourist-information spoken dialogue system. The IP problem is formulated as statistical decision making under uncertainty using Reinforcement Learning, where both content planning and attribute selection are jointly optimised based on data collected in a Wizard-of-Oz study. After earlier work testing and training this model in simulation, we now present results from an extensive online user study, involving 131 users and more than 800 test dialogues, which explores its contribution to overall 'global' task success. We find that the trained Information Presentation strategy significantly improves dialogue task completion, with up to a 9.7% increase (30% relative) compared to the deployed dialogue system which uses conventional, hand-coded presentation prompts. We also present subjective evaluation results and discuss the implications of these results for future work in dialogue management and NLG.