Consistent Goal-Directed User Model for Realisitc Man-Machine Task-Oriented Spoken Dialogue Simulation

Abstract

Because of the great variability of factors to take into account, designing a spoken dialogue system is still a tailoring task. Rapid design and reusability of previous work is made very difficult. For these reasons, the application of machine learning methods to dialogue strategy optimization has become a leading subject of researches this last decade. Yet, techniques such as reinforcement learning are very demanding in training data while obtaining a substantial amount of data in the particular case of spoken dialogues is time-consuming and therefore expansive. In order to expand existing data sets, dialogue simulation techniques are becoming a standard solution.In this paper we describe a user modeling technique for realistic simulation of man-machine goal-directed spoken dialogues. This model, based on a stochastic description of man-machine communication, unlike previously proposed models, is consistent along the interaction according to its history and a predefined user goal.

Human-Machine Dialogue as a Stochastic Game

“…Since (Levin and Pieraccini, 1997;Singh et al, 1999), only the DM is encoded as an RL agent, despite rare exceptions Chandramohan et al, 2012b;Chandramohan et al, 2012a)). The user is rather considered as a stationary agent modeled as a Bayesian net-work (Pietquin, 2006) or an agenda-based process (Schatzmann et al, 2007), leading to modeling errors (Schatztnann et al, 2005;Pietquin and Hastie, 2013).…”

A Generative Model for User Simulation in a Spatial Navigation Domain

“…Deterministic simulators with trainable parameters mitigate the lack of consistency using rules in conjunction with explicit goals or agendas (Scheffler and Young, 2002;Rieser and Lemon, 2006;Pietquin, 2006;Ai and Litman, 2007;Schatzmann and Young, 2009). However, they require large amounts of hand crafting and restrict the variability in user responses, which by extension restricts the access of the dialog manager to potentially interesting states.…”

Analysis of a new simulation approach to dialog system evaluation

“…As a consequence, the model is task-dependent. Pietquin (2006;2009) describes a new modeling approach which can be formalized as a Bayesian Network. As in Scheffler and Young's model, consistency is ensured by a description of the user's goal as a list of AVPs.…”