On-Line Processing of Grammatical Structure Using Reservoir Computing - Inria - Institut national de recherche en sciences et technologies du numérique
Communication Dans Un Congrès Année : 2012

On-Line Processing of Grammatical Structure Using Reservoir Computing

Xavier Hinaut
Peter Ford Dominey

Résumé

Previous words in the sentence can influence the processing of the current word in the timescale of hundreds of milliseconds. The current research provides a possible explanation of how certain aspects of this on-line language processing can occur, based on the dynamics of recurrent cortical networks. We simulate prefrontal area BA47 as a recurrent network that receives on-line input of "grammatical" words during sentence processing, with plastic connections between cortex and striatum (homology with Reservoir Computing). The system is trained on sentence-meaning pairs, where meaning is coded as activation in the striatum corresponding to the roles that different "semantic words" play in the sentences. The model learns an extended set of grammatical constructions, and demonstrates the ability to generalize to novel constructions. This demonstrates that a RNN can decode grammatical structure from sentences in an on-line manner in order to generate a predictive representation of the meaning of the sentences.
Fichier principal
Vignette du fichier
Hinaut2012_ICANN.pdf (564.15 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02561301 , version 1 (03-05-2020)

Identifiants

Citer

Xavier Hinaut, Peter Ford Dominey. On-Line Processing of Grammatical Structure Using Reservoir Computing. In A. E. P. Villa, et al.: Artificial Neural Networks and Machine Learning - ICANN 2012 - 22nd International Conference on Artificial Neural Networks, Sep 2012, Lausanne, Switzerland. pp.596-603, ⟨10.1007/978-3-642-33269-2_75⟩. ⟨hal-02561301⟩
40 Consultations
174 Téléchargements

Altmetric

Partager

More