Skip to Main content Skip to Navigation
Conference papers

An Incremental Approach to Language Acquisition: Thematic Role Assignment with Echo State Networks

Xavier Hinaut 1 Stefan Wermter 1
1 KT - Knowledge Technology group [Hamburg]
Department of Informatics [Hamburg]
Abstract : In previous research a model for thematic role assignment (θRARes) was proposed , using the Reservoir Computing paradigm. This language comprehension model consisted of a recurrent neural network (RNN) with fixed random connections which models distributed processing in the prefrontal cortex, and an output layer which models the striatum. In contrast to this previous batch learning method, in this paper we explored a more biological learning mechanism. A new version of the model (i-θRARes) was developed that permitted incremental learning, at each time step. Learning was based on a stochastic gradient descent method. We report here results showing that this incremental version was successfully able to learn a corpus of complex grammatical constructions, reinforcing the neurocognitive plausibility of the model from a language acquisition perspective.
Complete list of metadata

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/hal-02561290
Contributor : Xavier Hinaut <>
Submitted on : Sunday, May 3, 2020 - 6:06:22 PM
Last modification on : Sunday, November 22, 2020 - 12:34:06 PM

File

Hinaut_ICANN2014_CR.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Xavier Hinaut, Stefan Wermter. An Incremental Approach to Language Acquisition: Thematic Role Assignment with Echo State Networks. In: Wermter S. et al. (eds) Artificial Neural Networks and Machine Learning – ICANN 2014, Sep 2014, Hamburg, Germany. pp.33--40, ⟨10.1007/978-3-319-11179-7_5⟩. ⟨hal-02561290⟩

Share

Metrics

Record views

26

Files downloads

154