We might soon be able to fully read and better understand ancient Greek texts, thanks to a new artificial intelligence program (A.I) that could help fill in gaps and determine when and where they’re from.
The program’s developers published a paper in Nature earlier this year, detailing how their new A.I. system can reconstruct portions of missing or damaged inscriptions with an accuracy rate between 62 to 72 percent, depending on data input.
The program, which has been named Ithaca after the Greek island home of King Odysseus, was developed by Deep Mind, a subsidiary of Alphabet.
The team has been testing the accuracy of their program by using data from more than 60,000 well-studied ancient Greek texts, dated between 700 B.C. and 500 C.E. They would obscure some of the texts to help determine how accurately Ithaca filled in the missing portions.
Without assistance, Ithaca was able to restore texts with 62 percent accuracy; determine a text’s geographic origins 71 percent of the time; and date texts to within 30 years from when it was written, according to the study.
Historians working without benefit of the program could restore texts with only 25 percent accuracy. But when historians supplemented data from the A.I. system and added it to their own work, historical accuracy increased to 72 percent.
Featured image: Ancient Greek tablet at the Acropolis Museum in Athens, Greece. June 28, 2022. Photo by Darden Livesay.