How do we get there? Evaluating transformer neural networks as cognitive models for English past tense inflection

Neural network models have achieved good performance on morphological inflection tasks, including English past tense inflection. However whether they can represent human cognitive mechanisms is still under debate. In this work, we examined transformer models with different training size to show that: 1) neural models correlate with both human behaviors and cognitive theories' predictions on nonce verbs; and the model with small-size training data that matches parents' input distribution has the highest correlation; 2) neural models make different types of errors on regular and irregular verbs, exhibiting a clear distinction between regulars and irregulars. Therefore, we conclude that neural networks have the potential to be good cognitive models for English past tense.