Robustness of the Random Language Model

TL;DR

This paper investigates the robustness of the Random Language Model's transition to grammatical syntax, showing it withstands various extensions and relates to language acquisition in children and machine learning.

Contribution

It demonstrates the stability of the model's transition under realistic extensions and links the transition to language development and machine learning.

Findings

Transition is robust to symmetry breaking.

Transition can be observed by fixing deep structure and varying surface properties.

Transition resembles language acquisition in children around 24 months.

Abstract

The Random Language Model (De Giuli 2019) is an ensemble of stochastic context-free grammars, quantifying the syntax of human and computer languages. The model suggests a simple picture of first language learning as a type of annealing in the vast space of potential languages. In its simplest formulation, it implies a single continuous transition to grammatical syntax, at which the symmetry among potential words and categories is spontaneously broken. Here this picture is scrutinized by considering its robustness against extensions of the original model, and trajectories through parameter space different from those originally considered. It is shown here that (i) the scenario is robust to explicit symmetry breaking, an inevitable component of learning in the real world; and (ii) the transition to grammatical syntax can be encountered by fixing the deep (hidden) structure while varying the surface (observable) properties. It is also argued that the transition becomes a sharp thermodynamic transition in an idealized limit. Moreover, comparison with human data on the clustering coefficient of syntax networks suggests that the observed transition is equivalent to that normally experienced by children at age 24 months. The results are discussed in light of theory of first-language acquisition in linguistics, and recent successes in machine learning.