Fiche du document
13 mai 2020
- handle: 10670/1.409spi
- hal: hal-03482181
info:eu-repo/semantics/OpenAccess
Mots-clés
chunking machine learning CRF automatic segmentation of spoken data oral corpus kind of spoken discourseSujets proches
Learning, MachineCiter ce document
Iris Eshkol-Taravella et al., « Chunk Different Kind of Spoken Discourse: Challenges for Machine Learning », HAL-SHS : linguistique, ID : 10670/1.409spi
Métriques
Partage / Export
Résumé
This paper describes the development of a chunker for spoken data by supervised machine learning using the CRFs, based on a small reference corpus composed of two kinds of discourse: prepared monologue vs. spontaneous talk in interaction. The methodology considers the specific character of the spoken data. The machine learning uses the results of several available taggers, without correcting the results manually. Experiments show that the discourse type (monologue vs. free talk), the speech nature (spontaneous vs. prepared) and the corpus size can influence the results of the machine learning process and must be considered while interpreting the results.