Reading between the lines: learning to map high-level instructions to commands
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Assessing user simulation for dialog systems using human judges and automatic evaluation measures
Natural Language Engineering
Inverse reinforcement learning for interactive systems
Proceedings of the 2nd Workshop on Machine Learning for Interactive Systems: Bridging the Gap Between Perception, Action and Communication
Hi-index | 0.00 |
A key advantage of taking a statistical approach to spoken dialogue systems is the ability to formalise dialogue policy design as a stochastic optimization problem. However, since dialogue policies are learnt by interactively exploring alternative dialogue paths, conventional static dialogue corpora cannot be used directly for training and instead, a user simulator is commonly used. This paper describes a novel statistical user model based on a compact stack-like state representation called a user agenda which allows state transitions to be modeled as sequences of push- and pop-operations and elegantly encodes the dialogue history from a user's point of view. An expectation-maximisation based algorithm is presented which models the observable user output in terms of a sequence of hidden states and thereby allows the model to be trained on a corpus of minimally annotated data. Experimental results with a real-world dialogue system demonstrate that the trained user model can be successfully used to optimise a dialogue policy which outperforms a hand-crafted baseline in terms of task completion rates and user satisfaction scores.