Service interruption on Monday 11 July from 12:30 to 13:00: all the sites of the CCSD (HAL, EpiSciences, SciencesConf, AureHAL) will be inaccessible (network hardware connection).
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 Connect in order to contact the contributor
Submitted on : Monday, August 31, 2020 - 8:41:03 PM
Last modification on : Sunday, June 26, 2022 - 2:52:56 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