Apollo designed to fill gaps in damaged papyrus fragments using statistical likelihood
2 Sep 22 · 4d ago · 1 article · 1 source · development 2 of 2
The model is built to identify word divisions in ancient Greek text, weigh socio-political contexts, and fill blanks with the most statistically likely words or passages. This automates work previously requiring specialized scholars to manually restore damaged documents.
“If I had a machine telling me, 'Here are the three possible words that could fit into that gap,' it would speed up matters considerably.”
Armand D'AngourAustrian Academy of Science Releasing institutionMistral AI lab partnerSail Reply Technology services partnerStephen Colvin Classics and historical linguistics professor, University College LondonArmand D'Angour Classical languages and literature professor, University of Oxford
The whole story articlesposts the bright band is this development · numbered dots are the others · click one to jump
Reported in the same hours no headline names this development itself — these 1 claim were published in its stretch
-
first by Wired, 4d ago
All 2 developments of Austrian Academy releases Apollo, an AI model for ancient… →
NewswiresMastodonGoogle News