Separating Optical and Language Models through Encoder-Decoder Strategy for Transferable Handwriting Recognition

Adeline Granet 1, 2, 3 Emmanuel Morin 2, 3 Harold Mouchère 1, 3 Solen Quiniou 2, 3 Christian Viard-Gaudin 1, 3
1 IPI - Image Perception Interaction
LS2N - Laboratoire des Sciences du Numérique de Nantes
2 TALN - Traitement Automatique du Langage Naturel
LS2N - Laboratoire des Sciences du Numérique de Nantes
Abstract : Lack of data can be an issue when beginning a new study on historical handwritten documents. To deal with this, we propose a deep-learning based recognizer which separates the optical and the language models in order to train them separately using different resources. In this work, we present the optical encoder part of a multilingual transductive transfer learning applied to historical handwriting recognition. The optical encoder transforms the input word image into a non-latent space that depends only on the letter-n-grams: it enables it to be independent of the language. This transformation avoids embedding a language model and operating the transfer learning across languages using the same alphabet. The language decoder creates from a vector of letter-n-grams a word as a sequence of characters. Experiments show that separating optical and language model can be a solution for multilingual transfer learning.
Type de document :
Communication dans un congrès
ICFHR 16th International Conference on Frontiers in Handwriting Recognition , Aug 2018, Niagara Falls, Canada
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01821598
Contributeur : Adeline Granet <>
Soumis le : vendredi 22 juin 2018 - 15:41:28
Dernière modification le : mardi 10 juillet 2018 - 01:20:13

Fichier

 Accès restreint
Fichier visible le : 2018-12-22

Connectez-vous pour demander l'accès au fichier

Identifiants

  • HAL Id : hal-01821598, version 1

Collections

Citation

Adeline Granet, Emmanuel Morin, Harold Mouchère, Solen Quiniou, Christian Viard-Gaudin. Separating Optical and Language Models through Encoder-Decoder Strategy for Transferable Handwriting Recognition. ICFHR 16th International Conference on Frontiers in Handwriting Recognition , Aug 2018, Niagara Falls, Canada. 〈hal-01821598〉

Partager

Métriques

Consultations de la notice

25