Innovative Computer System Reconstructs Ancient Languages

An international team of scientists has used a new automated tool to reconstruct protolanguages – ancient tongues from which modern languages evolved.

This images shows an Austronesian phylogenetic tree produced by the system, left, the inset shows a portion of the Oceanic languages, where the Nuclear Polynesian family and Polynesian family are visible, the table shows a sample of reconstructions produced by the system (Alexandre Bouchard-Côté et al)

According to their paper published in the Proceedings of the National Academy of Sciences, the results are 85 per cent accurate when compared to the manual reconstructions performed by linguists.

“We’re hopeful our tool will revolutionize historical linguistics much the same way that statistical analysis and computer power revolutionized the study of evolutionary biology,” said Prof Alexandre Bouchard-Côté of the University of British Columbia, lead author on the study.

“And while our system won’t replace the nuanced work of skilled linguists, it could prove valuable by enabling them to increase the number of modern languages they use as the basis for their reconstructions.”

Protolanguages are reconstructed by grouping words with common meanings from related modern languages, analyzing common features, and then applying sound-change rules and other criteria to derive the common parent.

The new tool analyzes sound changes at the level of basic phonetic units, and can operate at much greater scale than previous computerized tools.

The team reconstructed a set of protolanguages from a database of more than 142,000 word forms from 637 Austronesian languages – spoken in Southeast Asia, the Pacific and parts of continental Asia.


Bibliographic information: Alexandre Bouchard-Côté et al. Automated reconstruction of ancient languages using probabilistic models of sound change. PNAS, published online before print February 11, 2013; doi: 10.1073/pnas.1204678110