Determining the relative importance of the elements in a sentence is a key factor for
effortless natural language understanding. For human language processing, we can …

Languages are governed by syntactic constraints—structural rules that determine which
sentences are grammatical in the language. In English, one such constraint is subject-verb …

Syntax is a central organizing component of human language but few models explain how it
may be implemented in neurons. We combined two rapid synaptic rules to demonstrate how …

Sentences of a language abide by rules called syntactic constraints which govern the form
those sentences may take. Verifying that these constraints are satisfied requires …

Previous work suggests that RNNs trained on natural language corpora can capture number
agreement well for simple sentences but perform less well when sentences contain …

LSTMs were introduced to mitigate the problem of vanishing gradients in standard recurrent
architectures. Pooling-based recurrent neural architectures consistently outperform their …