Are Automatic Methods for Cognate Detection Good Enough for Phylogenetic Reconstruction in Historical Linguistics?

TL;DR

This paper assesses how well automatic cognate detection algorithms perform in phylogenetic reconstruction of language families compared to traditional manual methods, finding they are a promising tool for broad linguistic analyses.

Contribution

It provides an empirical evaluation of automatic cognate detection methods' effectiveness in phylogenetic inference, highlighting their potential as a practical alternative to manual annotation.

Findings

Automated cognate sets produce phylogenies close to expert-annotated ones.

Automatic methods are especially useful for large-scale or exploratory studies.

Manual annotations still yield slightly more accurate phylogenies.

Abstract

We evaluate the performance of state-of-the-art algorithms for automatic cognate detection by comparing how useful automatically inferred cognates are for the task of phylogenetic inference compared to classical manually annotated cognate sets. Our findings suggest that phylogenies inferred from automated cognate sets come close to phylogenies inferred from expert-annotated ones, although on average, the latter are still superior. We conclude that future work on phylogenetic reconstruction can profit much from automatic cognate detection. Especially where scholars are merely interested in exploring the bigger picture of a language family's phylogeny, algorithms for automatic cognate detection are a useful complement for current research on language phylogenies.