Adapt a Text-Oriented Chunker for Oral Data: How Much Manual Effort is Necessary?

Abstract : In this paper, we try three distinct approaches to chunk transcribed oral data with labeling tools learnt from a corpus of written texts. The purpose is to reach the best possible results with the least possible manual correction or re-learning effort.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [8 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01174605
Contributor : Iris Eshkol, Eshkol-Taravella <>
Submitted on : Thursday, July 9, 2015 - 1:14:23 PM
Last modification on : Friday, November 9, 2018 - 1:44:02 PM
Document(s) archivé(s) le : Wednesday, April 26, 2017 - 1:43:35 AM

File

main.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01174605, version 1

Citation

Isabelle Tellier, Yoann Dupont, Iris Eshkol, Ilaine Wang. Adapt a Text-Oriented Chunker for Oral Data: How Much Manual Effort is Necessary?. 14th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL), Oct 2013, Hefei, China. 2013. 〈hal-01174605〉

Share

Metrics

Record views

177

Files downloads

87