Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Conversation as Action Under Uncertainty
UAI '00 Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence
Towards developing general models of usability with PARADISE
Natural Language Engineering
Trainable sentence planning for complex information presentation in spoken dialog systems
ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Learning to say it well: reranking realizations by predicted synthesis quality
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Hybrid reinforcement/supervised learning of dialogue policies from fixed data sets
Computational Linguistics
Optimizing dialogue management with reinforcement learning: experiments with the NJFun system
Journal of Artificial Intelligence Research
Individual and domain adaptation in sentence planning for dialogue
Journal of Artificial Intelligence Research
Learning lexical alignment policies for generating referring expressions in spoken dialogue systems
ENLG '09 Proceedings of the 12th European Workshop on Natural Language Generation
Learning human multimodal dialogue strategies
Natural Language Engineering
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
Optimising information presentation for spoken dialogue systems
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Phrase-based statistical language generation using graphical models and active learning
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Hierarchical reinforcement learning for adaptive text generation
INLG '10 Proceedings of the 6th International Natural Language Generation Conference
INLG '10 Proceedings of the 6th International Natural Language Generation Conference
Learning adaptive referring expression generation policies for spoken dialogue systems
Empirical methods in natural language generation
Construction and experiment of a spoken consulting dialogue system
IWSDS'10 Proceedings of the Second international conference on Spoken dialogue systems for ambient environments
Learning dialogue strategies from older and younger simulated users
SIGDIAL '10 Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue
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
Modeling spoken decision support dialogue and optimization of its dialogue strategy
ACM Transactions on Speech and Language Processing (TSLP)
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
An adaptive dialogue system with online dialogue policy learning
SETN'12 Proceedings of the 7th Hellenic conference on Artificial Intelligence: theories and applications
A comparative study of reinforcement learning techniques on dialogue management
EACL '12 Proceedings of the Student Research Workshop at the 13th Conference of the European Chapter of the Association for Computational Linguistics
Hi-index | 0.01 |
We present and evaluate a new model for Natural Language Generation (NLG) in Spoken Dialogue Systems, based on statistical planning, given noisy feedback from the current generation context (e.g. a user and a surface realiser). We study its use in a standard NLG problem: how to present information (in this case a set of search results) to users, given the complex tradeoffs between utterance length, amount of information conveyed, and cognitive load. We set these trade-offs by analysing existing match data. We then train a NLG policy using Reinforcement Learning (RL), which adapts its behaviour to noisy feedback from the current generation context. This policy is compared to several baselines derived from previous work in this area. The learned policy significantly outperforms all the prior approaches.