Are cascade dialogue state tracking models speaking out of turn in spoken dialogues? - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Are cascade dialogue state tracking models speaking out of turn in spoken dialogues?

Résumé

In Task-Oriented Dialogue (TOD) systems, correctly updating the system's understanding of the user's needs is key to a smooth interaction. Traditionally TOD systems are composed of several modules that interact with one another. While each of these components is the focus of active research communities, their behavior in interaction can be overlooked. This paper proposes a comprehensive analysis of the errors of state of the art systems in complex settings such as Dialogue State Tracking which highly depends on the dialogue context. Based on spoken MultiWoz, we identify that errors on non-categorical slots' values are essential to address in order to bridge the gap between spoken and chat-based dialogue systems. We explore potential solutions to improve transcriptions and help dialogue state tracking generative models correct such errors.
Fichier principal
Vignette du fichier
main.pdf (597.09 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04267783 , version 1 (02-11-2023)

Identifiants

  • HAL Id : hal-04267783 , version 1

Citer

Lucas Druart, Léo Jacqmin, Benoît Favre, Lina Maria Rojas-Barahona, Valentin Vielzeuf. Are cascade dialogue state tracking models speaking out of turn in spoken dialogues?. 2023. ⟨hal-04267783⟩
36 Consultations
18 Téléchargements

Partager

Gmail Facebook X LinkedIn More