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

In previous research a model for thematic role assignment (?RARes) 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-?RARes) 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.

@InProceedings{HW14a, 
 	 author =  {Hinaut, Xavier and Wermter, Stefan},  
 	 title = {An Incremental Approach to Language Acquisition: Thematic Role Assignment with Echo State Networks}, 
 	 booktitle = {Artificial Neural Networks and Machine Learning - ICANN 2014},
 	 editors = {Wermter, Stefan; Weber, Cornelius; Duch, Wlodislaw; Honkela, Timo; Koprinkova-Hristova, Petia; Magg, Sven; Palm, Günther; Villa, Alessandro E.P. },
 	 number = {},
 	 volume = {},
 	 pages = {33--40},
 	 year = {2014},
 	 month = {Sep},
 	 publisher = {Springer Heidelberg},
 	 doi = {10.1007/978-3-319-11179-7}, 
 }