Comparing Methods for Segmenting Elementary Discourse Units in a French Conversational Corpus - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Comparing Methods for Segmenting Elementary Discourse Units in a French Conversational Corpus

Résumé

While discourse segmentation and parsing has made considerable progress in recent years, discursive analysis of conversational speech remains a difficult issue. In this paper, we exploit a French data set that has been manually segmented into discourse units to compare two approaches to discourse segmentation: fine-tuning existing systems on manual segmentation vs. using hand-crafted labeling rules to develop a weakly supervised segmenter. Our results show that both approaches yield similar performance in terms of f-score while data programming requires less manual annotation work. In a second experiment we play with the amount of training data used for fine-tuning systems and show that a small amount of hand labeled data is enough to obtain good results (albeit not as good as when all available annotated data are used).
Fichier principal
Vignette du fichier
Nodalida_segmentation.pdf (329.98 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04222122 , version 1 (28-09-2023)

Identifiants

  • HAL Id : hal-04222122 , version 1

Citer

Laurent Prevot, Julie Hunter, Philippe Muller. Comparing Methods for Segmenting Elementary Discourse Units in a French Conversational Corpus. 24th Nordic Conference on Computational Linguistics (NoDaLiDa 2023), May 2023, Tórshavn, Faroe Islands, Finland. ⟨hal-04222122⟩
56 Consultations
15 Téléchargements

Partager

Gmail Facebook X LinkedIn More