Skip to Main content Skip to Navigation
Journal articles

Correction des erreurs orthographiques des systèmes de reconnaissance de l'écriture et de la parole arabe

Abstract : In this paper, we present two methods for correcting Arabic words generated by text and/or speech recognizers. These techniques operate as post-processors and they are conceived to be adaptable. They correct rejection and substitution word errors. The former one is very linked to the dictionary and is called 'lexicon driven', when the orther is very general exploiting contextual information and called 'context driven'. Arabic language properties are very useful in morpho-lexical analysis and so they were strongly exploited in the development of the second method. Substitution errors are rewritten in rules for being used by a rule based system. The extensions to the other levels of language analysis are considered in perspectives.
Document type :
Journal articles
Complete list of metadata

https://hal.inria.fr/hal-01261705
Contributor : Coordination Episciences Iam <>
Submitted on : Monday, January 25, 2016 - 5:12:35 PM
Last modification on : Wednesday, October 30, 2019 - 4:34:07 PM
Long-term archiving on: : Tuesday, April 26, 2016 - 11:37:26 AM

File

00201.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-01261705, version 1

Collections

Citation

Toufik Sari, Mokhtar Sellami. Correction des erreurs orthographiques des systèmes de reconnaissance de l'écriture et de la parole arabe. Revue Africaine de la Recherche en Informatique et Mathématiques Appliquées, INRIA, 2004, 2, pp.1-18. ⟨hal-01261705⟩

Share

Metrics

Record views

219

Files downloads

977