@article{Fischer2017,
title = {Beyond Pairwise Similarity: Quantifying and Characterizing Linguistic Similarity between Groups of Languages by MDL},
author = {Andrea Fischer and Jilles Vreeken and Dietrich Klakow},
url = {http://www.cys.cic.ipn.mx/ojs/index.php/CyS/article/view/2865},
year = {2017},
date = {2017},
journal = {Computación y Systems},
pages = {829-839},
volume = {21},
number = {4},
abstract = {<div>We present a minimum description length based algorithm for finding the regular correspondences between related languages and show how it can be used to quantify the similarity between not only pairs, but whole groups of languages directly from cognate sets. We employ a two-part code, which allows to use the data and model complexity of the discovered correspondences as information-theoretic quantifications of the degree of regularity of cognate realizations in these languages. Unlike previous work, our approach is not limited to pairs of languages, does not limit the size of discovered correspondences, does not make assumptions about the shape or distribution of correspondences, and requires no expert knowledge or fine-tuning of parameters. We here test our approach on the Slavic languages. In a pairwise analysis of 13 Slavic languages, we show that our algorithm replicates their linguistic classification exactly. In a four-language experiment, we demonstrate how our algorithm efficiently quantifies similarity between all subsets of the analyzed four languages and find that it is excellently suited to quantifying the orthographic regularity of closely-related languages.</div>},
pubstate = {published},
type = {article}
}