[Article] Comparing VMS with 80+ other languages

[DonaldFisk]

Thanks for sharing this with us.

What is the advantage of t-SNE over other dimensional reduction techniques such as PCA?

One obvious way of identifying an unknown language is phonotactics.   Alphabetic scripts are to a large extent phonetic, so analysing adjacent letters, or commonly occurring groups of letters, would be a promising approach.   (Perhaps your N-gram approach partially addressed this.)   Also, did you try to recognize parts of speech, either through their position relative to nearby words or through their inflection patterns?   Finally, it would be good to exclude languages which are impossible given the manuscript's known provenance, such as Guarani, and very improbable, such as Yoruba or Japanese.

I used a phonotactic approach on the assumption it's plaintext (or a simple substitution cipher, which for an unknown script is really the same thing), and identified an unlikely though historically plausible language candidate (Abkhaz).   I think it's highly unlikely that it is Abkhaz, or any other language, and didn't (indeed, can't, given Abkhaz's obscurity) follow it up to prove it either way.   My analysis and reason for considering Abkhaz are here: You are not allowed to view links. Register or Login to view..

There are a few minor mistakes in the paper.   Scottish Gaelic, which I can read, is a modern language (it has its own television channel, BBC Alba) and didn't even exist in the middle ages: it's a direct descendant of Middle Irish.   It, and its close relative Irish, are unusual in two important respects: their grammar, which is superficially closer to Semitic languages than other non-Celtic European languages, and their spelling system, so not surprisingly it's a linguistic outlier.  Also, Tagalog is spoken in the Philippines, quite a long way from Australia.