Archaeologists have uncovered many examples of ancient written languages yet to be deciphered. In most cases, the trick to deciphering extinct writing systems is to trace the evolution of that system backward – for instance, the Cyrillic alphabet evolved from the Greek alphabet, itself an evolution of the Phoenician alphabet.
In order to assist with deciphering writing systems, researchers and students at MIT have developed software that can decipher unknown scripts by comparing them to those we understand:
A computer successfully deciphered an ancient language Ugaritic in just a couple of hours.
Regina Barzilay, an associate professor in MIT’s Computer Science and Artificial Intelligence Lab, Ben Snyder, a grad student in her lab, and the University of Southern California’s Kevin Knight are the creators. [...]
The system makes certain assumption of the language’s similarity to another, Hebrew in this case. It also depends on a systematic way to map the alphabet of one language on to the alphabet of the other.
And it assumes a similar mapping for parts of words. A word like “overloading,” for instance, has both a prefix – “over” – and a suffix – “ing.”
“We iterate through the data hundreds of times, thousands of times and each time, our guesses have higher probability, because we’re actually coming closer to a solution where we get more consistency,” said Snyder.
While the software isn’t threatening to put human deciphers out of work, the developers say it does have the potential to make their jobs a bit easier.