A procedure for unsupervised lexicon learning

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

We describe an incremental unsupervised procedure to learn words from transcribed continuous speech. The algorithm is based on a conservative and traditional statistical model, and results of empirical tests show that it is competitive with other algorithms that have been proposed recently for this task.
Expanded version of this paper appears in Computational Linguistics 27(3)

Keywords

Computation and Language, I.2.6;I.2.7

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/30936

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/cs/0111064
 http://arxiv.org/abs/cs/0111064
 Proceedings of the eighteenth international conference on machine learning, ICML-01, pp.569--576, 2001

Collections

arXiv