Toufik Sari ; Mokhtar Sellami - Correction des erreurs orthographiques des systèmes de reconnaissance de l'écriture et de la parole arabe

arima:2555 - Revue Africaine de la Recherche en Informatique et Mathématiques Appliquées, October 22, 2004, Volume 2, 2004-2005 - https://doi.org/10.46298/arima.2555
Correction des erreurs orthographiques des systèmes de reconnaissance de l'écriture et de la parole arabe

Authors: Toufik Sari ; Mokhtar Sellami

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.


Volume: Volume 2, 2004-2005
Published on: October 22, 2004
Submitted on: March 26, 2004
Keywords: Arabic character recognition, error detection, word correction, arabic linguistic, probabilistic rule-based techniques, post-processing.,OCR arabe,détection des erreurs,correction des mots,langue arabe,analyse morpho-lexicale,post-traitement,base de règles.,[INFO] Computer Science [cs],[MATH] Mathematics [math]


Share

Consultation statistics

This page has been seen 80 times.
This article's PDF has been downloaded 198 times.