Communication Dans Un Congrès Année : 2025

Locating strongly informative utterances in conversation using multimodal cues

Résumé

Interaction theories argue that mutual understanding between speakers in natural conversations arises from building shared knowledge (common ground), but no model specifies what information is retained or under what conditions. Previous studies have used Information Theory metrics to quantify the dynamics of information exchanged between participants but lack an efficient way to identify which information becomes common ground. These attempts furthermore limited themselves to the study of conversation transcripts, overlooking nonverbal cues like visuals and intonation. To address this, we propose a method for annotating new corpora using models trained on a subset of annotated utterances. Results show a fair applicability (κ 0.3) across corpora, though this is strongly modulated by the conversational task being investigated.

Fichier principal
Vignette du fichier
locatingstrongly_0511.pdf (539.78 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05115173 , version 1 (16-06-2025)
hal-05115173 , version 2 (02-07-2025)

Licence

Identifiants

  • HAL Id : hal-05115173 , version 2

Citer

Eliot Maës, Philippe Blache, Leonor Becerra-Bonache. Locating strongly informative utterances in conversation using multimodal cues. Proceedings of the Annual Meeting of the Cognitive Science Society, The Cognitive Science Society, Jul 2025, San Francisco, CA US, United States. ⟨hal-05115173v2⟩
339 Consultations
282 Téléchargements

Partager

  • More