A Priori and A Posteriori Integration and Combination of Language Models in an On-Line Handwritten Sentence Recognition System

Solen Quiniou 1, * Eric Anquetil 1
* Auteur correspondant
1 IMADOC - Interprétation et Reconnaissance d’Images et de Documents
UR1 - Université de Rennes 1, INSA Rennes - Institut National des Sciences Appliquées - Rennes, CNRS - Centre National de la Recherche Scientifique : UMR6074
Abstract : This paper investigates the integration of different language models into an on-line sentence recognition system. The impact of n-gram and n-class (based on statistically and on morpho-syntactically classes) models, built on the Brown corpus, is compared in terms of word recognition rate. Furthermore, their integration in different steps of the recognition process (during it or to rescore the N-best list of proposed sentences) is considered, thus showing better performances when used the sooner. Combinations of these models are also studied, in addition to the integration in the aforementioned recognition steps. All experiments are carried out on sentences from the Brown corpus which were written by several writers.
Type de document :
Communication dans un congrès
International Workshop on Frontiers in Handwriting Recognition, Oct 2006, La Baule, France. pp.403-408, 2006
Liste complète des métadonnées

Littérature citée [18 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00580645
Contributeur : Solen Quiniou <>
Soumis le : lundi 28 mars 2011 - 18:43:45
Dernière modification le : lundi 14 janvier 2019 - 10:00:06
Document(s) archivé(s) le : mercredi 29 juin 2011 - 03:00:28

Fichier

quiniou06aPriori.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00580645, version 1

Citation

Solen Quiniou, Eric Anquetil. A Priori and A Posteriori Integration and Combination of Language Models in an On-Line Handwritten Sentence Recognition System. International Workshop on Frontiers in Handwriting Recognition, Oct 2006, La Baule, France. pp.403-408, 2006. 〈hal-00580645〉

Partager

Métriques

Consultations de la notice

187

Téléchargements de fichiers

45