Understanding texts written using an unknown system in a tongue that’s been dead for thousands of years is quite the challenge. Reconstructing missing bits of the ancient text is even harder – though admittedly, if one gets it wrong, who’s to know?Ms. Schuster links to the underlying article in PNAS: Restoration of fragmentary Babylonian texts using recurrent neural networks (Ethan Fetaya, Yonatan Lifshitz, Elad Aaron, and Shai Gordin). The article is behind a subscription wall, but you can read the abstract.
Filling in missing text starts with being able to read and understand the original text. That requires much donkey work. Now an Israeli team led by Shai Gordin at Ariel University in the West Bank has reinvented the donkey in digital form, harnessing artificial intelligence to help complete fragmented Akkadian cuneiform tablets.
The algorithm looks like a useful tool, but it still (for now!) requires a good bit of human intervention to operate. For other posts on algorithms being applied to cuneiform studies, archaeology, paleography, and epigraphy, see here and links, here, here, and here.
Visit PaleoJudaica daily for the latest news on ancient Judaism and the biblical world.