Planning and Acting under Uncertainty: A New Model for Spoken Dialogue Systems

Source: DBLP

ABSTRACT Uncertainty plays a central role in spoken dialogue systems. Some stochastic
models like Markov decision process (MDP) are used to model the dialogue
manager. But the partially observable system state and user intention hinder
the natural representation of the dialogue state. MDP-based system degrades
fast when uncertainty about a user's intention increases. We propose a novel
dialogue model based on the partially observable Markov decision process
(POMDP). We use hidden system states and user intentions as the state set,
parser results and low-level information as the observation set, domain actions
and dialogue repair actions as the action set. Here the low-level information
is extracted from different input modals, including speech, keyboard, mouse,
etc., using Bayesian networks. Because of the limitation of the exact
algorithms, we focus on heuristic approximation algorithms and their
applicability in POMDP for dialogue management. We also propose two methods for
grid point selection in grid-based approximation algorithms.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Control in spoken dialog systems is challenging largely because automatic speech recognition is unreliable, and hence the state of the conversation can never be known with certainty. Partially observable Markov decision processes (POMDPs) provide a principled mathematical framework for planning and control in this context; however, POMDPs face severe scalability challenges, and past work has been limited to trivially small dialog tasks. This paper presents a novel POMDP optimization technique-composite summary point-based value iteration (CSPBVI)-which enables optimization to be performed on slot-filling POMDP-based dialog managers of a realistic size. Using dialog models trained on data from a tourist information domain, simulation results show that CSPBVI scales effectively, outperforms non-POMDP baselines, and is robust to estimation errors.
    IEEE Transactions on Audio Speech and Language Processing 10/2007; · 1.68 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A common problem for real-world POMDP applications is how to incorporate expert knowledge and constraints such as business rules into the optimization process. This paper de-scribes a simple approach created in the course of developing a spoken dialog system. A POMDP and conventional hand-crafted dialog controller run in parallel; the conventional dia-log controller nominates a set of one or more actions, and the POMDP chooses the optimal action. This allows designers to express real-world constraints in a familiar manner, and also prunes the search space of policies. The method nat-urally admits compression, and the POMDP value function can draw on features from both the POMDP belief state and the hand-crafted dialog controller. The method has been used to build a full-scale dialog system which is currently running at AT&T Labs. An evaluation shows that this unified archi-tecture yields better performance than using a conventional dialog manager alone, and also demonstrates an improvement in optimization speed and reliability vs. a pure POMDP.
  • [Show abstract] [Hide abstract]
    ABSTRACT: The HRI-2013 Workshop on Probabilistic Approaches for Robot Control in Human-Robot Interaction (PARC-HRI) brings together researchers to discuss the application of probabilistic approaches to further enable robot autonomy in HRI, as well as to address the shortcomings and necessary improvements in current techniques needed for robust socially intelligent behavior. This half day workshop investigates the use of probabilistic approaches, such as Bayesian networks and Markov models, for robust robot control and decision-making under uncertainty. Target applications range from social behavior primitives—such as gesture, eye gaze, and spacing—to higher-level interaction planning and management systems.
    Human-Robot Interaction (HRI), 2013 8th ACM/IEEE International Conference on; 01/2013

Full-text (3 Sources)

Available from
Jul 6, 2014