Number Theory Meets Linguistics: Modelling Noun Pluralisation Across 1497 Languages Using 2-adic Metrics
Computation and Language
2022-11-24 v1 Number Theory
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.
Keywords
Cite
@article{arxiv.2211.13124,
title = {Number Theory Meets Linguistics: Modelling Noun Pluralisation Across 1497 Languages Using 2-adic Metrics},
author = {Gregory Baker and Diego Molla-Aliod},
journal= {arXiv preprint arXiv:2211.13124},
year = {2022}
}
Comments
Accepted into AACL-IJCNLP 2022