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.
Complete list of metadatas

Cited literature [10 references]  Display  Hide  Download

https://hal.inria.fr/hal-01417060
Contributor : Xavier Hinaut <>
Submitted on : Thursday, December 15, 2016 - 11:33:54 AM
Last modification on : Thursday, February 7, 2019 - 4:33:47 PM
Long-term archiving on : Thursday, March 16, 2017 - 4:44:07 PM

File

ICDL-Epirob_Workshop-on-langua...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01417060, version 1

Citation

Xavier Hinaut. Recurrent Neural Network for Syntax Learning with Flexible Representations. IEEE ICDL-EPIROB Workshop on Language Learning, Dec 2016, Cergy, France. ⟨hal-01417060⟩

Share

Metrics

Record views

544

Files downloads

339