Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learner

TL;DR

This paper advocates for a comprehensive reverse-engineering approach to infant language acquisition using machine learning and wearable tech, emphasizing full data complexity and realistic evaluation to deepen scientific understanding.

Contribution

It proposes a new framework for modeling early language development that incorporates raw sensory data and realistic testing, advancing beyond simplified models.

Findings

Preliminary results demonstrate the feasibility of the proposed approach.

Models can pass psycholinguist tests at multiple linguistic levels.

Shared, privacy-preserving data repositories are essential for progress.

Abstract

During their first years of life, infants learn the language(s) of their environment at an amazing speed despite large cross cultural variations in amount and complexity of the available language input. Understanding this simple fact still escapes current cognitive and linguistic theories. Recently, spectacular progress in the engineering science, notably, machine learning and wearable technology, offer the promise of revolutionizing the study of cognitive development. Machine learning offers powerful learning algorithms that can achieve human-like performance on many linguistic tasks. Wearable sensors can capture vast amounts of data, which enable the reconstruction of the sensory experience of infants in their natural environment. The project of 'reverse engineering' language development, i.e., of building an effective system that mimics infant's achievements appears therefore to be within reach. Here, we analyze the conditions under which such a project can contribute to our scientific understanding of early language development. We argue that instead of defining a sub-problem or simplifying the data, computational models should address the full complexity of the learning situation, and take as input the raw sensory signals available to infants. This implies that (1) accessible but privacy-preserving repositories of home data be setup and widely shared, and (2) models be evaluated at different linguistic levels through a benchmark of psycholinguist tests that can be passed by machines and humans alike, (3) linguistically and psychologically plausible learning architectures be scaled up to real data using probabilistic/optimization principles from machine learning. We discuss the feasibility of this approach and present preliminary results.