The possible relationship between Basque and Iberian has inspired a great deal of study that dates back at least to the 16th century, when the idea that Basque was the language that had originally been spoken throughout the Iberian Peninsula began to gain general currency.  That was the start of Basque-Iberianism.  After centuries of debate, the question about the existence, or lack thereof, of a relationship is still open.

Yesterday, the Computer Science & Artificial Intelligence Lab (CSAIL) at the Massachusetts Institute of Technology (MIT) published an article explaining that the researchers had created an automatic learning system that allows a computer to automatically decypher a lost language without the need for advanced knowledge of its relationship to other languages.

According to the report, these researchers have proven that this system, on its own, can determine the relationships between languages, and they used it to corroborate recent studies that suggest that the Iberian language is not really related to Basque.

They state that the proposed algorithm can evaluate the proximity of two languages; in fact, when tested with known languages, it can even precisely identify language families.  The team applied its algorithm to Iberian, searching for its relationships with Basque, as well as with other, less probable, candidates, including the Romance, Germanic, Turkish, and Uralic families.  While it is true that Basque and Latin were closer to each other than Iberian to other languages, they were still too different to be considered related.

We honestly really want to dig deeper into the work and discover further conclusions.  But we imagine that this article, concise enough to almost be a telegraph, will be just the first entry in a much deeper study that will be released soon enough, with the in-depth conclusions the researchers have reached.

We’ll leave you with the report on the CSAIL website at MIT, sure than this will be a very popular topic that will spark a lively debate among enthusiasts and students of the language of the Basques.

CSAIL – 21/10/2020 – USA

Translating lost languages using machine learning

Recent research suggests that most languages that have ever existed are no longer spoken. Dozens of these dead languages are also considered to be lost, or “undeciphered” — that is, we don’t know enough about their grammar, vocabulary, or syntax to be able to actually understand their texts.

(Follow) (Automatic translation)