The Architecture of a Biologically Plausible Language Organ

TL;DR

This paper introduces a biologically plausible neural model of a language organ that learns nouns and verbs from grounded input using Hebbian plasticity, simulating early language acquisition in infants.

Contribution

It presents a novel biologically inspired neural architecture capable of learning language components without backpropagation, advancing understanding of language development in the brain.

Findings

Successfully learned nouns and verbs from limited input

Demonstrated learning through Hebbian plasticity without backpropagation

Extended previous models by incorporating biological plausibility for language acquisition

Abstract

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.