Language discrimination and clustering via a neural network approach
Disordered Systems and Neural Networks
2015-07-16 v1 Computation and Language
Neural and Evolutionary Computing
Physics and Society
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.
Cite
@article{arxiv.1507.04116,
title = {Language discrimination and clustering via a neural network approach},
author = {Angelo Mariano and Giorgio Parisi and Saverio Pascazio},
journal= {arXiv preprint arXiv:1507.04116},
year = {2015}
}
Comments
10 pages, 12 figures