Implementation of a Statistical Dialogue Manager for Commercial Conversational Systems

2020 ◽  
pp. 383-393
Author(s):  
Pablo Cañas ◽  
David Griol
Keyword(s):  
Dialogue Manager

Evaluation of a dialogue manager for a mobile robot

2013 ◽  
Author(s):  
Marcelo Quindere ◽  
Luis Seabra Lopes ◽  
Antonio J. S. Teixeira
Keyword(s):  
Mobile Robot ◽  
Dialogue Manager

Dialogue Manager for a NLIDB for Solving the Semantic Ellipsis Problem in Query Formulation

2010 ◽  
pp. 203-213 ◽  
Author(s):  
Rodolfo A. Pazos R. ◽  
Juan C. Rojas P. ◽  
René Santaolaya S. ◽  
José A. Martínez F. ◽  
Juan J. Gonzalez B.
Keyword(s):  
Query Formulation ◽  
Dialogue Manager

scholarly journals A tractable hybrid DDN–POMDP approach to affective dialogue modeling for probabilistic frame-based dialogue systems

2009 ◽  
Vol 15 (2) ◽  
pp. 273-307 ◽  
Author(s):  
TRUNG H. BUI ◽  
MANNES POEL ◽  
ANTON NIJHOLT ◽  
JOB ZWIERS
Keyword(s):  
Affective State ◽  
Observation Error ◽  
Dialogue Systems ◽  
Dialogue Model ◽  
Management Domain ◽  
Novel Approach ◽  
Look Ahead ◽  
Markov Decision ◽  
The One ◽  
Dialogue Manager

AbstractWe propose a novel approach to developing a tractable affective dialogue model for probabilistic frame-based dialogue systems. The affective dialogue model, based on Partially Observable Markov Decision Process (POMDP) and Dynamic Decision Network (DDN) techniques, is composed of two main parts: the slot-level dialogue manager and the global dialogue manager. It has two new features: (1) being able to deal with a large number of slots and (2) being able to take into account some aspects of the user's affective state in deriving the adaptive dialogue strategies. Our implemented prototype dialogue manager can handle hundreds of slots, where each individual slot might have hundreds of values. Our approach is illustrated through a route navigation example in the crisis management domain. We conducted various experiments to evaluate our approach and to compare it with approximate POMDP techniques and handcrafted policies. The experimental results showed that the DDN–POMDP policy outperforms three handcrafted policies when the user's action error is induced by stress as well as when the observation error increases. Further, performance of the one-step look-ahead DDN–POMDP policy after optimizing its internal reward is close to state-of-the-art approximate POMDP counterparts.

scholarly journals A Conventional Dialogue Model Based on Dialogue Patterns

2017 ◽  
Vol 26 (01) ◽  
pp. 1760009 ◽  
Author(s):  
Guillaume Dubuisson Duplessis ◽  
Alexandre Pauchet ◽  
Nathalie Chaignaud ◽  
Jean-Philippe Kotowicz
Keyword(s):  
Open Source ◽  
Software Agent ◽  
Management Process ◽  
Dialogue Model ◽  
Dialogue Management ◽  
Dialogue Games ◽  
Human Interactions ◽  
Model Based ◽  
Dialogue Game ◽  
Dialogue Manager

Our work aims at designing a dialogue manager dedicated to agents that interact with humans. In this article, we investigate how dialogue patterns at the dialogue act level extracted from Human-Human interactions can be fruitfully used by a software agent to interact with a human.We show how these patterns can be leveraged via a dialogue game structure in order to benefit to the dialogue management process of an agent. We describe how empirically specified dialogue games can be employed on both interpretative and generative levels of dialogue management. We present Dogma, an open-source module that can be used by an agent to manage its conventional communicative behaviour. We show that our library of dialogue games can be used into Dogma to generate fragments of dialogue that are strongly coherent from a human perspective.

Sign in / Sign up

Export Citation Format

Share Document