Skip to Main content Skip to Navigation
Conference papers

Language Acquisition with Echo State Networks: Towards Unsupervised Learning

Thanh Trung Dinh 1 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 : The modeling of children language acquisition with robots is a long quest paved with pitfalls. Recently a sentence parsing model learning in cross-situational conditions has been proposed: it learns from the robot visual representations. The model, based on random recurrent neural networks (i.e. reservoirs), can achieve significant performance after few hundreds of training examples, more quickly that what a theoretical model could do. In this study, we investigate the developmental plausibility of such model: (i) if it can learn to generalize from single-object sentence to double-object sentence; (ii) if it can use more plausible representations: (ii.a) inputs as sequence of phonemes (instead of words) and (ii.b) outputs fully independent from sentence structure (in order to enable purely unsupervised cross-situational learning). Interestingly, tasks (i) and (ii.a) are solved in a straightforward fashion, whereas task (ii.b) suggest that that learning with tensor representations is a more difficult task
Complete list of metadata

Cited literature [21 references]  Display  Hide  Download
Contributor : Xavier Hinaut <>
Submitted on : Monday, August 31, 2020 - 8:41:03 PM
Last modification on : Friday, February 19, 2021 - 11:13:43 AM
Long-term archiving on: : Tuesday, December 1, 2020 - 1:03:50 PM


Files produced by the author(s)


  • HAL Id : hal-02926613, version 1



Thanh Trung Dinh, Xavier Hinaut. Language Acquisition with Echo State Networks: Towards Unsupervised Learning. ICDL 2020 - IEEE International Conference on Development and Learning, Oct 2020, Valparaiso / Virtual, Chile. ⟨hal-02926613⟩



Record views


Files downloads