More than 2,000 years after Plato died, the towering figure of Classical Antiquity and founder of the Academy, considered by many to be the first university in the west, can still make headlines.
Researchers claimed this week that they had found the final resting place of the Greek philosopher, a patch in the garden of his Athens Academy, after scanning an ancient papyrus scroll recovered from the library of a Herculaneum villa buried when Mount Vesuvius erupted in AD 79.
The project is part of a new wave of efforts that seek to read, restore and translate ancient and even lost languages using the latest technology. Armed with modern tools, many powered by artificial intelligence, scholars are beginning to read what has long been considered unreadable.
“It’s going to have a huge impact,” said Dr Kilian Fleischer, a papyrologist who worked on The History of the Academy, the scroll that revealed details of Plato’s life. “There will be scrolls that will be read with these new techniques that add to our knowledge of antiquity, and to our knowledge of literature in general. It might be a second renaissance.”
The History of the Academy, written by the first century Epicurean philosopher Philodemus, has been studied for many years and modern editions exist. The researchers’ aim was to produce a more comprehensive edition. This is no easy task when the scroll is in pieces from being unrolled and the papyrus is as black as the ink written on it. Substantial portions of text are faint, missing or illegible.
Prof Graziano Ranocchia, project leader at the University of Pisa, used hyperspectral imaging to illuminate the scroll fragments with broadband infrared light. The images reveal letters that are invisible to the naked eye, giving scholars important clues about the missing words. Fleischer compares it to completing a crossword or the game Hangman: sometimes it only takes a single letter to be sure of the answer.
“It’s an amazing feeling, this moment to read something new and know that it’s information that other researchers have wanted for decades or centuries,” Fleischer said. “We’re traveling back and seeing text that hasn’t been read for 2,000 years.”
Armed with the scans, the team reconstructed 20% to 30% more of the text, with the additional words put in place amounting to 1,000 extra letters. The words for “buried” and “garden” do not appear in the scroll itself – it is suspected from other characters and context.
Seeing the manuscript emerge was “a miracle,” Ranocchia said. A section at the end of the scroll is particularly exciting, he added. Philodemus mentions one or possibly two still unknown books about the Megarians and the Cynics. “It’s very important to us,” he said. The books may be among the hundreds of charred and unopened scrolls in the National Library in Naples, he said, or may even be buried at the doomed villa.
For many scholars, the prospect of reading the unopened Herculaneum Scrolls is very exciting. Carbonized in the explosion that overwhelmed Herculaneum, the scrolls are too fragile to physically unroll. But researchers led by Brent Seales, a computer scientist at the University of Kentucky, have shown there is no need. The team developed techniques to virtually unfold CT scans of the scrolls, and trained machine learning algorithms to detect ink on the distorted, blackened pages, often by detecting subtle changes in the patterns of the papyrus fibers.
The work led to the Vesuvius Challenge, a competition backed by Silicon Valley entrepreneurs, with lucrative prizes for the team that deciphered the most text from scans of scroll fragments. In February, three computer literate students shared the grand prize of $700,000 (£557,000). after reading hundreds of Greek words across 15 columns of the scroll. Dr Federica Nicolardi, a papyrologist at the University of Naples Federico II, studies one of the columns in which Philodemus discusses how perception begets knowledge when images “bump into our sense organs”.
The contents of the remaining rolls are up for debate. Some may be Latin texts. There might be poems by Sappho, Mark Anthony’s treatise on drunkenness, perhaps early writings on the Judeo-Christian tradition. Some of the scrolls are glued together, which may shed light on how ancient libraries were organized.
Nat Friedman, founding sponsor of the challenge, announced a further set of prizes to encourage researchers to read 90% of a scroll by the end of this year. A major bottleneck is the tedious process of “segmentation,” which involves manually tracing layers of the digital scroll so that the text-reading algorithm doesn’t confuse one warped layer with another. Work is underway to automate the process, which Friedman says will be a massive breakthrough. “It has to unlock reams and reams of text,” he said. In anticipation, Friedman booked nearly two weeks of beam time at the Diamond Light Source in Oxfordshire to potentially scan dozens more Herculaneum scrolls.
The new wave of technologies will shed light on more than the Herculaneum scrolls. The same approach can read papyri wrapped around Egyptian mummies, with sheets ranging from letters to laundry lists. There are boxes of the stuff in the back rooms of museums.
Dr Thea Sommerschield, a historian and epigrapher at the University of Nottingham, and colleagues recently examines how machine learning is applied to ancient languages. The tools, they concluded, reshaped the field in much the same way that the microscope and telescope transformed science.
Sommerschield and Yannis Assael at Google DeepMind are co-leaders on a project called Ithaca, an AI program based on a transformer, the technology behind ChatGPT. It is available to everyone and can predict missing characters in Ancient Greek inscriptions and suggest times and places where they were made possible. The tool, used hundreds of times a week, promises to shed new light on the ancient world. Inscriptions in stone, ceramics and metals preserve writings from around the world and from a cross-section of society, including women and slaves, not just emperors and the elite. “They give us information about thought, language, society and politics of the ancient world in general,” Sommerschield said.
So far, the best results have come from multidisciplinary teams with computer engineers working with scholars. Such mixed teams are essential, Sommerschield said, as are efforts to build clean and well-curated datasets that cover not only Ancient Greek and other popular languages, but writings from around the world. “If we have that kind of interaction, we will earn the trust and interest and engagement of computer scientists, the general public and the scientific communities,” she added.
