Recurrent babbling: evaluating the acquisition of grammar from limited input data

In contrast with previous models: (i) we train a Artificial Neural Networks, and Long Short-Term vanilla char-LSTM on a more realistic variety and Memory Networks more specifically, have consistently amount of data, focusing on a limited amount of demonstrated great capabilities in the area child-directed language; (ii) we do not rely on extrinsic of language modeling. In addition to generating evaluations or downstream tasks, instead we credible surface patterns, they show excellent performances introduce a methodology to evaluate how the distribution when tested on very specific grammatical of grammatical items, over time, comes abilities (Gulordava et al., 2018; Lakretz et al., to approximate the one in the input, through a continuous 2019), without requiring any prior bias towards the process and (iii) we tentatively explore the syntactic structure of natural languages.