Number Theory Meets Linguistics: Modelling Noun Pluralisation Across 1497 Languages Using 2-adic Metrics

TL;DR

This paper introduces a novel approach to modeling noun pluralization across 1497 languages using p-adic metrics, demonstrating significant improvements over traditional Euclidean methods in certain language families.

Contribution

It presents a simple linear regression model leveraging p-adic metrics for pluralization, outperforming Euclidean regressors on diverse language families.

Findings

P-adic regression outperforms Euclidean methods in several language families.

Limited evidence supports modeling noun declensions as p-adic neighborhoods.

The approach bridges number theory and linguistics for morphological modeling.

Abstract

A simple machine learning model of pluralisation as a linear regression problem minimising a p-adic metric substantially outperforms even the most robust of Euclidean-space regressors on languages in the Indo-European, Austronesian, Trans New-Guinea, Sino-Tibetan, Nilo-Saharan, Oto-Meanguean and Atlantic-Congo language families. There is insufficient evidence to support modelling distinct noun declensions as a p-adic neighbourhood even in Indo-European languages.