The Information State Approach to Dialogue Management

By David R. Traum, Staffan Larsson. 2003

416 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Conceptual spatial representations for indoor mobile robots (2008, methodology): “Furthermore, whereas RoboVie and BIRON use finite state machines to model dialogue behavior, we combine information states [23], like Godot, together with a task-oriented perspective, as WITAS or Mel.”
Multimodal Interfaces: A Survey of Principles, Models and Frameworks (2009, background): “…and probabilistic approaches : these approaches try to describe human-machine dialog following information states, consisting of five main components: informational components, formal representations of those components, a set of dialog moves, a set of update rules and an update strategy [68].”
MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling (2018, background): “, 2013); the need to integrate third-party services and dialogue context in the decision-making (Traum and Larsson, 2003; Paek and Pieraccini, 2008); and finally, the ability to generate natural and engaging responses (Stent et al.”
A Corpus of Controlled Opinionated and Knowledgeable Movie Discussions for Training Neural Conversation Models (2020, background): “…dialogue modelling used to be mostly rule-based with the dialogue being driven by pre-speciﬁed knowledge representations (e.g., (Bobrow et al., 1977), (Traum and Larsson, 2003), (Stede and Schlangen, 2004)), recent years have seen efforts of basing this task on models directly learned from data.”