A Biologically Plausible SOM Representation of the Orthographic Form of 50,000 French Words - Aix-Marseille Université Accéder directement au contenu
Chapitre D'ouvrage Année : 2014

A Biologically Plausible SOM Representation of the Orthographic Form of 50,000 French Words

Résumé

Recently, an important aspect of human visual word recognition has been characterized. The letter position is encoded in our brain using an explicit representation of order based on letter pairs: the open-bigram coding [15]. We hypothesize that spelling has evolved in order to minimize reading errors. Therefore, word recognition using bigrams — instead of letters — should be more efficient. First, we study the influence of the size of the neighborhood, which defines the number of bigrams per word, on the performance of the matching between bigrams and word. Our tests are conducted against one of the best recognition solutions used today by the industry, which matches letters to words. Secondly, we build a cortical map representation of the words in the bigram space — which implies numerous experiments in order to achieve a satisfactory projection. Third, we develop an ultra-fast version of the self-organizing map in order to achieve learning in minutes instead of months.
Fichier principal
Vignette du fichier
Touzet-WSOM2014(1).pdf (574.22 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01338033 , version 1 (27-06-2016)

Identifiants

Citer

Claude Touzet, Christopher Kermorvant, Hervé Glotin. A Biologically Plausible SOM Representation of the Orthographic Form of 50,000 French Words. Advances in Self-Organizing Maps and Learning Vector Quantization, 295, Springer pp.303-312, 2014, AISC ⟨10.1007/978-3-319-07695-9_29⟩. ⟨hal-01338033⟩
241 Consultations
225 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More