A Comprehensive Comparison of Neural Networks as Cognitive Models of Inflection
This research addresses a debate in cognitive science and NLP about modeling human inflection processing, providing incremental insights by comparing architectures on specific tasks.
The study tackled the problem of whether neural networks can model human cognitive processing of inflectional morphology by measuring correlations between human judgments and neural network probabilities for unknown word inflections in English past tense and German number tasks. It found that Transformers may better account for human behavior than LSTMs, with specific features that improve accuracy not always enhancing human-likeness.
Neural networks have long been at the center of a debate around the cognitive mechanism by which humans process inflectional morphology. This debate has gravitated into NLP by way of the question: Are neural networks a feasible account for human behavior in morphological inflection? We address that question by measuring the correlation between human judgments and neural network probabilities for unknown word inflections. We test a larger range of architectures than previously studied on two important tasks for the cognitive processing debate: English past tense, and German number inflection. We find evidence that the Transformer may be a better account of human behavior than LSTMs on these datasets, and that LSTM features known to increase inflection accuracy do not always result in more human-like behavior.