Learning inflection classes using Adaptive Resonance Theory

TL;DR

This paper demonstrates that Adaptive Resonance Theory neural networks can unsupervisedly learn and cluster verbal inflection classes in languages, showing potential for studying morphological acquisition and language change.

Contribution

It introduces a cognitively plausible neural network model for unsupervised learning of inflection classes, aligning computational results with linguistic descriptions.

Findings

Optimal performance occurs at specific generalisation parameters.

The model's features align with linguistic inflection class descriptions.

Performance varies with inflectional system complexity.

Abstract

The concept of inflection classes is an abstraction used by linguists, and provides a means to describe patterns in languages that give an analogical base for deducing previously unencountered forms. This ability is an important part of morphological acquisition and processing. We study the learnability of a system of verbal inflection classes by the individual language user by performing unsupervised clustering of lexemes into inflection classes. As a cognitively plausible and interpretable computational model, we use Adaptive Resonance Theory, a neural network with a parameter that determines the degree of generalisation (vigilance). The model is applied to Latin, Portuguese and Estonian. The similarity of clustering to attested inflection classes varies depending on the complexity of the inflectional system. We find the best performance in a narrow region of the generalisation parameter. The learned features extracted from the model show similarity with linguistic descriptions of the inflection classes. The proposed model could be used to study change in inflection classes in the future, by including it in an agent-based model.