ADAM: A Sandbox for Implementing Language Learning

TL;DR

ADAM is a flexible Python-based software platform that simulates grounded language learning in children using virtual environments, enabling researchers to design and test various language acquisition models.

Contribution

It introduces a modular system for simulating child language learning with grounded perception, facilitating experimentation with different curricula and algorithms.

Findings

Supports diverse language learning experiments

Enables testing of cognitively plausible algorithms

Provides open-source code for community use

Abstract

We present ADAM, a software system for designing and running child language learning experiments in Python. The system uses a virtual world to simulate a grounded language acquisition process in which the language learner utilizes cognitively plausible learning algorithms to form perceptual and linguistic representations of the observed world. The modular nature of ADAM makes it easy to design and test different language learning curricula as well as learning algorithms. In this report, we describe the architecture of the ADAM system in detail, and illustrate its components with examples. We provide our code.