Communication Dans Un Congrès Année : 2024

Investigating Discourse Segmentation in Taiwan Southern Min Spontaneous Speech

Résumé

In recent years, discourse segmentation has received increased attention; however the majority of studies have focused on written genres and languages with abundant linguistic resources. This paper investigates discourse segmentation of a spontaneous speech corpus in Taiwan Southern Min. We compare finetuning a Language Model (LLM) using two approaches: supervised, taking advantage of a high-quality annotated dataset, and weaklysupervised, which requires only a small amount of manual labeling. The corpus used here is transcribed in both Chinese characters and romanized script. This allows us to assess the impact of the written form on the discourse segmentation task. Moreover, the dataset includes manual prosodic break labeling, allowing an exploration of the role prosody can play in contemporary discourse segmentation systems grounded in LLMs. In our study, the supervised approach outperforms weak-supervision; the character-based version demonstrates better scores compared to the romanized version; and prosodic information proves to be an interesting source to increase discourse segmentation performance.

Fichier principal
Vignette du fichier
2024.codi-1.5 (1).pdf (1.62 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05110523 , version 1 (13-06-2025)

Licence

Identifiants

  • HAL Id : hal-05110523 , version 1

Citer

Laurent Prevot, Sheng-Fu Wang. Investigating Discourse Segmentation in Taiwan Southern Min Spontaneous Speech. Proceedings of the 5th Workshop on Computational Approaches to Discourse (CODI 2024), Mar 2024, Malta, France. ⟨hal-05110523⟩
76 Consultations
128 Téléchargements

Partager

  • More