What Artificial Neural Networks Can Tell Us About Human Language Acquisition

Rapid progress in machine learning for natural language processing has the potential to transform debates about how humans learn language. However, the learning environments and biases of current artificial learners and humans diverge in ways that weaken the impact of the evidence obtained from learning simulations. For example, today's most effective neural language models are trained on roughly one thousand times the amount of linguistic data available to a typical child. To increase the relevance of learnability results from computational …

acquisition artificial artificial neural networks biases cs.cl current environments evidence example human humans impact language language acquisition language processing learn machine machine learning natural natural language natural language processing networks neural networks processing progress simulations