# Learning inflection classes using Adaptive Resonance Theory

arXiv: https://arxiv.org/abs/2512.15551 · HTML: https://mlsanity.com/paper/2512.15551/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 98 references that are in the map.
- First posted on arXiv 17 Dec 2025.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection](https://mlsanity.com/paper/1810.07125/) (2018)
- [CoNLL-SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection in 52 Languages](https://mlsanity.com/paper/1706.09031/) (2017)
- [SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection](https://mlsanity.com/paper/2006.11572/) (2020)
- [Minimum adjusted Rand index for two clusterings of a given size](https://mlsanity.com/paper/2002.03677/) (2020)
- [A Survey of Adaptive Resonance Theory Neural Network Models for Engineering Applications](https://mlsanity.com/paper/1905.11437/) (2019)
- [Predicting Declension Class from Form and Meaning](https://mlsanity.com/paper/2005.00626/) (2020)
- [On the Diachronic Stability of Irregularity in Inflectional Morphology](https://mlsanity.com/paper/1804.08262/) (2018)
- [Computational Morphology with Neural Network Approaches](https://mlsanity.com/paper/2105.09404/) (2021)
- [The role of attraction-repulsion dynamics in simulating the emergence of inflectional class systems](https://mlsanity.com/paper/2111.08465/) (2021)

## Abstract (arXiv)

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.