A groundbreaking artificial intelligence system called Aeneas is poised to transform the study of ancient Roman inscriptions, offering historians a faster and more accurate way to reconstruct the past, researchers said.
Developed by Dr. Thea Sommerschield of Nottingham University and Dr. Yannis Assael of Google DeepMind, Aeneas analyzes incomplete inscriptions and identifies missing words, approximate dates, and possible locations by drawing on a vast dataset of 176,000 Roman texts.
Historians typically spend years comparing damaged inscriptions with similar texts, but Aeneas performs this analysis in seconds. It uses advanced algorithms to find linguistic and stylistic parallels, which help scholars reconstruct degraded texts carved on monuments and artifacts.
“Inscriptions are the earliest forms of writing,” Sommerschield said. “Interpreting them is like solving a gigantic jigsaw puzzle with tens of thousands of pieces, of which 90 percent are lost.”
Cambridge University’s Prof Dame Mary Beard described the technology as “transformative,” noting that Aeneas expands the scope of what is possible in historical research. “Breakthroughs in this very difficult field have tended to rely on the memory, the subjective judgement and the hunch/guesswork of individual scholars,” Beard said. “Aeneas opens up entirely new horizons.”
The tool was recently tested on the Res Gestae Divi Augusti, a famous inscription found in Ankara, Turkey. It successfully narrowed the likely date range to between 10 and 20 CE, closely matching what many experts had previously concluded.
In trials involving 23 historians, researchers found that combining Aeneas with expert input produced more accurate outcomes than either working alone.
While AI can make errors, Dr. Assael emphasized that the system is designed to support—not replace—human researchers. “What the historian can’t do is assess these parallels in a matter of seconds across tens of thousands of inscriptions,” he said. “That is where AI can come in as an assistant.”
The project highlights the growing role of artificial intelligence in decoding ancient texts and accelerating discovery across disciplines.
Related Readings:
