Mind Matters Natural and Artificial Intelligence News and Analysis
Fresco at Palace of Knossos in Crete
Fresco at Palace of Knossos in Crete

How a Searchable Database Is Helping Decipher a Lost Language

A cryptographer “solved” Minoan B from ancient Cretan culture in the 1950s but Minoan A remained a mystery until recently

There was once a flourishing civilization on the island of Crete called the Minoan culture (3000–11100 B.C.). Two languages are associated with it, Minoan A and, later, Minoan B. Minoan B was deciphered but Minoan A has remained a mystery that has “tormented linguists for many decades,” as Patricia Klaus puts it. Deciphering it would give us a window back as far as 1800 BC.:

Linear A, which was used by the Minoans during the Bronze Age, exists on at least 1,400 known inscriptions made on clay tablets. The language has baffled the world’s top archaeologists and linguistic experts for many years.

Patricia Claus, “Minoan Language Linear A Linked to Linear B in Groundbreaking New Research” at Greek Reporter (May 13, 2021)

So most of what we know is simply the many works of art and architecture they left to posterity:

Sometimes, we can break codes if we make fresh assumptions. For example, in 1952, cryptographer Michael Ventris (1922–1956) broke broke Minoan B, which was used on Crete after 1400 B.C., by making two key new assumptions: Many repeated words were place names on the island and the language was an early variant of Greek. Both those assumptions turned out to be correct when tested.

Now, fresh thinking may be helping with Minoan A: Cambridge classicist Ester Salgarella (pictured) turned the problem over to the internet. By creating a searchable online database of all writing in Linear A, she was able to get scholars more easily involved in detecting significant patterns more easily. It’s becoming clear that, contrary to what scholars formerly thought, Minoan A is probably an early version of Minoan B, written differently. Researchers still haven’t got very far with translating it but just knowing what they are looking for speeds up the work.

Salgarella explains “Collecting the Linear A inscriptions in a unified database is of paramount importance to be able to answer sophisticated paleographical and linguistic questions about the Linear A script as well as the Minoan language it encodes, which will help us reconstruct the socio-historical context of the Minoan civilization.”

Professor Tim Whitmarsh, the A.G. Leventis Professor of Greek Culture and Fellow of St. John’s, had high praise for Salgarella’s work. “Cracking Linear B was a huge post-war triumph for Classics, but Linear A has remained elusive.

“Dr. Salgarella has demonstrated that Linear B is closely related to its mysterious and previously illegible predecessor. She has brought us one step closer to understanding it. It’s an extraordinary piece of detective work.”

Here’s more on the mysterious Linear A:

Later, researchers may be able to turn some of the work over to artificial intelligence algorithms. But first they need to learn enough to tell the machine what to look for.

Here are some other ways AI is helping researchers unlock the past:

Does AI challenge Biblical archeology? Sadly, many surviving documents are so damaged that they cannot be read using traditional methods. The more scrolls are deciphered using new AI methods, the more archeologists will have to study and write about.

Can AI help us decipher lost languages? That depends mainly on the reasons we haven’t yet deciphered ancient texts in the past. AI can speed up translation of ancient documents where only a few scholars know the language. Whether it can help with mysterious unknown languages like Minoan A is another question.

How much can new AI tell us about ancient times? An ambitious new project hopes to use the predictive text that cell phones use to unlock their stories. Researchers face conundrums when using neural networks to figure out what people in the ancient past were thinking.


Can AI prove that Shakespeare had ghostwriters? An author’s unique style is like a fingerprint. AI can fill it in. Turning AI loose on some of these vexing problems should give literary scholars more to write about rather than less. The AI verdict may not always be right but it is bound to be food for thought.

Mind Matters News

Breaking and noteworthy news from the exciting world of natural and artificial intelligence at MindMatters.ai.

How a Searchable Database Is Helping Decipher a Lost Language