Diacritics Restoration for Arabic Dialects - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Diacritics Restoration for Arabic Dialects

Résumé

In this paper we present a statistical approach for automatic diacritization of Algiers dialectal texts. This approach is based on statistical machine translation. We first investigate this approach on Modern Standard Arabic (MSA) texts using several data sources and extrapolated the results on available dialectal texts. For evaluation we used word and diacritization error rates and also precision and recall.
Fichier principal
Vignette du fichier
PropalInterspeech.pdf (129.14 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00925815 , version 1 (08-01-2014)

Identifiants

  • HAL Id : hal-00925815 , version 1

Citer

Salima Harrat, Mourad Abbas, Karima Meftouh, Kamel Smaïli. Diacritics Restoration for Arabic Dialects. INTERSPEECH 2013 - 14th Annual Conference of the International Speech Communication Association, ISCA, Aug 2013, Lyon, France. ⟨hal-00925815⟩
382 Consultations
493 Téléchargements

Partager

Gmail Facebook X LinkedIn More