Automatic Measures to Characterise Verbal Alignment in Human-Agent Interaction - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Automatic Measures to Characterise Verbal Alignment in Human-Agent Interaction

Résumé

This work aims at characterising verbal alignment processes for improving virtual agent communicative capabilities. We propose computationally inexpensive measures of verbal alignment based on expression repetition in dyadic textual dialogues. Using these measures, we present a contrastive study between Human-Human and Human-Agent dialogues on a negotiation task. We exhibit quantitative differences in the strength and orientation of verbal alignment showing the ability of our approach to characterise important aspects of verbal alignment.
Fichier principal
Vignette du fichier
SIGDIAL10.pdf (160.31 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-01577813 , version 1 (28-08-2017)

Identifiants

  • HAL Id : hal-01577813 , version 1

Citer

Guillaume Dubuisson Duplessis, Chloé Clavel, Frédéric Landragin. Automatic Measures to Characterise Verbal Alignment in Human-Agent Interaction. 18th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), Aug 2017, Saarbrücken, Germany. pp.71-81. ⟨hal-01577813⟩
307 Consultations
303 Téléchargements

Partager

Gmail Facebook X LinkedIn More