Is one brick enough to break the wall of spoken dialogue state tracking? - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Is one brick enough to break the wall of spoken dialogue state tracking?

Valentin Vielzeuf
  • Fonction : Auteur
  • PersonId : 1016921
Yannick Estève

Résumé

In Task-Oriented Dialogue (TOD) systems, correctly updating the system's understanding of the user's needs (a.k.a dialogue state tracking) is key to a smooth interaction. Traditionally, TOD systems perform this update in three steps: transcription of the user's utterance, semantic extraction of the key concepts, and contextualization with the previously identified concepts. Such cascade approaches suffer from cascading errors and separate optimization. End-to-End approaches have been proved helpful up to the semantic extraction step. This paper goes one step further paving the path towards completely neural spoken dialogue state tracking by comparing three approaches: (1) a state of the art cascade approach, (2) a locally E2E approach with rule-based contextualization and (3) a completely neural approach.
Fichier principal
Vignette du fichier
main.pdf (1.13 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04267804 , version 1 (02-11-2023)
hal-04267804 , version 2 (04-12-2023)

Identifiants

Citer

Lucas Druart, Valentin Vielzeuf, Yannick Estève. Is one brick enough to break the wall of spoken dialogue state tracking?. 2023. ⟨hal-04267804v2⟩

Collections

UNIV-AVIGNON LIA
52 Consultations
19 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More