The Architecture of a Biologically Plausible Language Organ
This addresses the challenge of how infants acquire language biologically, offering a plausible model beyond existing parsers, though it is incremental in extending prior work.
The paper tackles the problem of language acquisition by simulating a biologically plausible language organ that learns nouns, verbs, and their meanings from grounded input using Hebbian plasticity without backpropagation, achieving success in this early step with only a modest number of sentences.
We present a simulated biologically plausible language organ, made up of stylized but realistic neurons, synapses, brain areas, plasticity, and a simplified model of sensory perception. We show through experiments that this model succeeds in an important early step in language acquisition: the learning of nouns, verbs, and their meanings, from the grounded input of only a modest number of sentences. Learning in this system is achieved through Hebbian plasticity, and without backpropagation. Our model goes beyond a parser previously designed in a similar environment, with the critical addition of a biologically plausible account for how language can be acquired in the infant's brain, not just processed by a mature brain.