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
Towards developing general models of usability with PARADISE
Natural Language Engineering
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
Trainable sentence planning for complex information presentation in spoken dialog systems
ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Data-driven user simulation for automated evaluation of spoken dialog systems
Computer Speech and Language
Mixture model POMDPs for efficient handling of uncertainty in dialogue management
HLT-Short '08 Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers
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
Learning contrastive connectives in sentence realization ranking
SIGdial '08 Proceedings of the 9th SIGdial Workshop on Discourse and Dialogue
Training and evaluation of the HIS POMDP dialogue system in noise
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
SIGDIAL '09 Proceedings of the SIGDIAL 2009 Conference: The 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Learning to adapt to unknown users: referring expression generation in spoken dialogue systems
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Learning to adapt to unknown users: referring expression generation in spoken dialogue systems
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
INLG '10 Proceedings of the 6th International Natural Language Generation Conference
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
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
Talkin' bout a revolution (statistically speaking)
ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation
Adaptive information presentation for spoken dialogue systems: evaluation with human subjects
ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation
ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation
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
Optimising incremental generation for spoken dialogue systems: reducing the need for fillers
INLG '12 Proceedings of the Seventh International Natural Language Generation Conference
Hi-index | 0.00 |
We present a novel approach to Information Presentation (IP) in Spoken Dialogue Systems (SDS) using a data-driven statistical optimisation framework for content planning and attribute selection. First we collect data in a Wizard-of-Oz (WoZ) experiment and use it to build a supervised model of human behaviour. This forms a baseline for measuring the performance of optimised policies, developed from this data using Reinforcement Learning (RL) methods. We show that the optimised policies significantly outperform the baselines in a variety of generation scenarios: while the supervised model is able to attain up to 87.6% of the possible reward on this task, the RL policies are significantly better in 5 out of 6 scenarios, gaining up to 91.5% of the total possible reward. The RL policies perform especially well in more complex scenarios. We are also the first to show that adding predictive "lower level" features (e.g. from the NLG realiser) is important for optimising IP strategies according to user preferences. This provides new insights into the nature of the IP problem for SDS.