Recurrent Neural Network for Syntax Learning with Flexible Predicates for Robotic Architectures

Xavier Hinaut (1, 2) , Johannes Twiefel (2) , Stefan Wermter (2)

1 Mnemosyne - Mnemonic Synergy
2 KT - Knowledge Technology group [Hamburg]

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 (i.e. predicates). We have previously shown that this ESN is able to generalize to unknown sentence structures. Moreover, it is able to learn English, French or both at the same time. The are two novelties presented here: (1) the encapsulation of this RNN in a ROS module enables one to use it in a robotic architecture like the Nao humanoid robot, and (2) the flexibility of the predicates it can learn to produce (e.g. extracting adjectives) enables one to use the model to explore language acquisition in a developmental approach.

Mots clés: recurrent neural network; echo state networks; human-robot interaction; language acquisition; reservoir computing; thematic role assignment

Domaines: Réseau de neurones [cs.NE]; Apprentissage [cs.LG]; Linguistique; Robotique [cs.RO]

Xavier Hinaut, Johannes Twiefel, Stefan Wermter. Recurrent Neural Network for Syntax Learning with Flexible Predicates for Robotic Architectures. The Sixth Joint IEEE International Conference Developmental Learning and Epigenetic Robotics (ICDL-EPIROB), Sep 2016, Cergy, France. ⟨hal-01417697⟩