Language discrimination and clustering via a neural network approach

TL;DR

This paper employs neural networks to classify Indo-European languages from text, creating a language distance measure, constructing a dendrogram, and analyzing the language subgroup structure based on an entropic criterion.

Contribution

It introduces a neural network-based method to quantify language similarities and reveals hierarchical language groupings through dendrogram analysis.

Findings

Identification of four or five language subgroups

Neural network-derived language distance measure

Hierarchical clustering of Indo-European languages

Abstract

We classify twenty-one Indo-European languages starting from written text. We use neural networks in order to define a distance among different languages, construct a dendrogram and analyze the ultrametric structure that emerges. Four or five subgroups of languages are identified, according to the "cut" of the dendrogram, drawn with an entropic criterion. The results and the method are discussed.