Recurrent Neural Network for Syntax Learning with Flexible Representations

Xavier Hinaut 1
1 Mnemosyne - Mnemonic Synergy
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest, IMN - Institut des Maladies Neurodégénératives [Bordeaux]
Abstract : We present a Recurrent Neural Network (RNN), namely an Echo State Network (ESN), that performs sentence comprehension and can be used for Human-Robot Interaction (HRI). The RNN is trained to map sentence structures to meanings (e.g. predicates). We have previously shown that this ESN is able to generalize to unknown sentence structures in English and French. The meaning representations it can learn to produce are flexible: it enables one to use any kind of " series of slots " (or more generally a vector representation) and are not limited to predicates. Moreover, preliminary work has shown that the model could be trained fully incrementally. Thus, it enables the exploration of language acquisition in a developmental approach. Furthermore, an " inverse " version of the model has been also studied, which enables to produce sentence structure from meaning representations. Therefore, if these two models are combined in a same agent, one can investigate language (and in particular syntax) emergence through agent-based simulations. This model has been encapsulated in a ROS module which enables one to use it in a cognitive robotic architecture, or in a distributed agent simulation.
Liste complète des métadonnées

Littérature citée [10 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01417060
Contributeur : Xavier Hinaut <>
Soumis le : jeudi 15 décembre 2016 - 11:33:54
Dernière modification le : jeudi 11 janvier 2018 - 06:24:26
Document(s) archivé(s) le : jeudi 16 mars 2017 - 16:44:07

Fichier

ICDL-Epirob_Workshop-on-langua...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01417060, version 1

Collections

Citation

Xavier Hinaut. Recurrent Neural Network for Syntax Learning with Flexible Representations. IEEE ICDL-EPIROB Workshop on Language Learning, Dec 2016, Cergy, France. 2016, 〈https://sites.google.com/site/epirob2016language/〉. 〈hal-01417060〉

Partager

Métriques

Consultations de la notice

256

Téléchargements de fichiers

102