Corpus ID: 17859837

Statistical User Simulation with a Hidden Agenda

@inproceedings{Schatzmann2007StatisticalUS,
  title={Statistical User Simulation with a Hidden Agenda},
  author={J. Schatzmann and Blaise Thomson and S. Young},
  booktitle={SIGDIAL},
  year={2007}
}
Recent work in the area of probabilistic user simulation for training statistical dialogue managers has investigated a new agenda-based user model and presented preliminary experiments with a handcrafted model parameter set. [...] Key Method Treating the user agenda as a hidden variable, the forward/backward algorithm can then be successfully applied to iteratively estimate the model parameters on dialogue data. © 2007 Association for Computational Linguistics.Expand
The Hidden Agenda User Simulation Model
TLDR
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 is described. Expand
Parameter estimation for agenda-based user simulation
This paper presents an agenda-based user simulator which has been extended to be trainable on real data with the aim of more closely modelling the complex rational behaviour exhibited by real users.Expand
Training a BN-based user model for dialogue simulation with missing data
TLDR
This contribution proposes the use of a previously developed user simulation system based on Bayesian Networks and the training of this model using algorithms dealing with missing data and shows that this training method increases the simulation performance in terms of similarity with real dialogues. Expand
User Simulation in the Development of Statistical Spoken Dialogue Systems
TLDR
This chapter provides an overview of user simulation techniques and evaluation methodologies, in particular, recent developments in Agenda-based user simulation, dynamic Bayesian network-based simulations and inverse reinforcement learning- based user simulations are discussed. Expand
A Sequence-to-Sequence Model for User Simulation in Spoken Dialogue Systems
TLDR
A data-driven user simulator based on an encoder-decoder recurrent neural network that outperforms an agenda-based simulator and an n-gram simulator, according to F-score, and is shown how this model can be used on the original action space and thereby models user behaviour with finer granularity. Expand
Error simulation for training statistical dialogue systems
TLDR
A novel approach to error simulation based on statistical models for word-level utterance generation, ASR confusions, and confidence score generation that explicitly models the context-dependent acoustic confusability of words and allows the system specific language model and semantic decoder to be incorporated. Expand
Setting Up User Action Probabilities in User Simulations for Dialog System Development
TLDR
This study compares estimating user probabilities from a small user data set versus handcrafting the probabilities, and discusses the pros and cons of both solutions for different dialog system development tasks. Expand
A Corpus-free State2Seq User Simulator for Task-oriented Dialogue
TLDR
A new corpus-free framework that builds a user simulator by first generating diverse dialogue data from templates and then building a new State2Seq user simulator on the data to efficiently leverage dialogue state and history. Expand
Data-driven user simulation for automated evaluation of spoken dialog systems
TLDR
A novel integrated dialog simulation technique for evaluating spoken dialog systems using a linear-chain conditional random field, and a two-phase data-driven domain-specific user utterance simulation method and a linguistic knowledge-based ASR channel simulation method are presented. Expand
A survey on metrics for the evaluation of user simulations
TLDR
A survey of User Simulations Metrics in the literature is given, some extensions are proposed and these metrics are discussed in terms of a list of desired features. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 20 REFERENCES
Agenda-Based User Simulation for Bootstrapping a POMDP Dialogue System
TLDR
This paper investigates the problem of bootstrapping a statistical dialogue manager without access to training data and proposes a new probabilistic agenda-based method for simulating user behaviour and shows that the learned policy was highly competitive, with task completion rates above 90%. Expand
A survey of statistical user simulation techniques for reinforcement-learning of dialogue management strategies
TLDR
The role of the dialogue manager in a spoken dialogue system is summarized, a short introduction to reinforcement-learning of dialogue management strategies is given, the literature on user modelling for simulation-based strategy learning is reviewed and recent work on user model evaluation is described. Expand
Automatic learning of dialogue strategy using dialogue simulation and reinforcement learning
TLDR
Q-learning with eligibility traces was applied to obtain policies for a telephone-based cinema information system, and the policies outperformed handcrafted policies that operated in the same restricted state space, and gave performance similar to the original design that had been through several iterations of manual refinement. Expand
Learning user simulations for information state update dialogue systems
TLDR
Two methods for simulating user behaviour in spoken dialogue systems using n-grams of speech act, task pairs and a normalised exponential output function are described and compared. Expand
Training a real-world POMDP-based Dialog System
TLDR
A new approach to policy optimisation based on grid-based Q-learning with a summary of belief space is discussed, and a technique for bootstrapping the system using a novel agenda-based user model is presented. Expand
The Hidden Information State Approach to Dialog Management
TLDR
A variation of the classic POMDP called the hidden information state (HIS) model is described in which belief distributions are represented efficiently by grouping states together into partitions and policy optimisation is made tractable by using a master to summary space mapping. Expand
Scaling up POMDPs for Dialog Management: The ``Summary POMDP'' Method
  • J.D. Williams, S. Young
  • Computer Science
  • IEEE Workshop on Automatic Speech Recognition and Understanding, 2005.
  • 2005
TLDR
This work presents a novel method for scaling slot-filling POMDP-based dialog managers to cope with tasks of a realistic size and shows that summary PomDP policies are reasonably robust to variations in user behavior. Expand
A stochastic model of human-machine interaction for learning dialog strategies
TLDR
The experimental results show that it is indeed possible to find a simple criterion, a state space representation, and a simulated user parameterization in order to automatically learn a relatively complex dialog behavior, similar to one that was heuristically designed by several research groups. Expand
Cluster-based user simulations for learning dialogue strategies
TLDR
A cluster -based technique for building user simula-tions which are varying, but complete and consistent with respect to real users is presented and the S U P E R evaluation metric is introduced to evaluate user simulations withrespect to thesedesiderata. Expand
Talking to machines (statistically speaking)
TLDR
This paper reviews spoken dialogue systems from a statistical modelling perspective and samples of existing work are reviewed, including dialogue control and optimisation, semantic interpretation, goal detection, natural language generation and synthesis. Expand
...
1
2
...