Communication Dans Un Congrès Année : 2018

Unsupervised Word Segmentation: does tone matter ?

Résumé

In this paper, we investigate the usefulness of tonal features for unsupervised word discovery, taking Mboshi, a low-resource tonal language from the Bantu family, as our main target language. In a preliminary step, we show that tone annotation improves the performance of \emph{supervised learning} when using a simplified representation of the data. To leverage this information in an unsupervised setting, we then present a probabilistic model based on a hierarchical Pitman-Yor process that incorporates tonal representations in its backoff structure. We compare our model with a tone-agnostic baseline and analyze if and how tone helps unsupervised segmentation on our small dataset.

Fichier principal
Vignette du fichier
Godard18doestone.pdf (273.78 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-01910756 , version 1 (08-10-2021)

Licence

Identifiants

  • HAL Id : hal-01910756 , version 1

Citer

Pierre Godard, Kevin Löser, Alexandre Allauzen, Laurent Besacier, François Yvon. Unsupervised Word Segmentation: does tone matter ?. International Conference on Intelligent Text Processing and Computational Linguistics, Mar 2018, Hanoï, Vietnam. ⟨hal-01910756⟩
247 Consultations
202 Téléchargements

Partager

  • More