Abstract Representation-neutral dialogue systems and methods (“RNDS”) are described that
include multi-application, multi-device spoken-language dialogue systems based on the …

A syntax tree or standard semantic representation can be represented as a set of indexed
constraints. This paper describes how this idea can be used in task oriented dialogue sys …

Le but de cette thèse est d'étudier de façon détaillée l'impact des disfluences en français
parlé (répétitions, auto-corrections, amorces, etc.) sur l'analyse syntaxique automatique de …

Les récents progrès de la synthèse de la parole ont redéfini les enjeux majeurs de la
communication personne-machine, qui s' articulent désormais autour du concept de …

We describe an implemented spoken-language dialogue system for a travel-planning
domain, which accesses a commercially available travelinformation web-server and …

We present RUBISC, a new incremental chunker that can perform incremental slot filling and
revising as it receives a stream of words. Slot values can influence each other via a …

The development of spoken dialogue systems is often limited by the performance of their
speech recognition component. The impact of speech recognition errors on dialogue …

The purpose of this deliverable is to discuss the requirements for a dialogue system
architecture for the Siridus Project and describe a baseline architecture for the initial Siridus …

Les systèmes de dialogue Oral Homme-Machine actuellement opérationnels sont conçus
pour les tâches extrêmement précises. Leur développement dépend directement de celui de …

Dialogue utterances are rarely sentences and are often fragmentary. This paper discusses
some of the implicit assumptions made by shallow and deep processing approaches, and …