More than 2,000 years after Plato’s death, 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 the front pages of the news.
This week, researchers claimed to have found the Greek philosopher’s final resting place, a patch in the garden of his Academy in Athens, after scanning an ancient papyrus scroll recovered from the library of a villa in Herculaneum that was buried when Mount Vesuvius erupted in 79 AD
The project belongs to a new wave of efforts seeking to read, restore and translate ancient and even lost languages with cutting-edge technologies. Armed with modern tools, many of them powered by artificial intelligence, academics are beginning to read what was long 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 contribute to our knowledge of antiquity, and our knowledge of literature in general. “This could be a second renaissance.”
The History of the Academy, written by the Epicurean philosopher Philodemus in the 1st century, has been studied for many years and modern editions exist. The researchers’ goal was to produce a more complete edition. It is not an easy task when the parchment is in pieces from being unrolled and the papyrus is as black as the ink written on it. Substantial portions of the text are faded, missing, or illegible.
Professor 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 crucial clues about the missing words. Fleischer compares it to completing a crossword puzzle or the game of hangman: sometimes a single letter is enough to be sure of the answer.
“It’s a wonderful feeling this moment to read something new and know that it was information that other researchers have wanted for decades or centuries,” Fleischer said. “We are traveling back and seeing a text that has not been read in 2,000 years.”
Armed with the scans, the team reconstructed 20% to 30% more of the text, and the extra words placed in its place amounted to 1,000 extra letters. The words for “buried” and “garden” do not appear on the scroll itself; They are conjectures based on other characters and context.
Watching the manuscript emerge was “a marvel,” Ranocchia said. A passage at the end of the scroll was particularly moving, she added. Philodemus mentions one or possibly two still unknown books about the Megarians and the Cynics. “That’s very important to us,” he said. The books may be among the hundreds of charred, unopened scrolls in the National Library in Naples, he said, or perhaps even still buried in the condemned villa.
For many scholars, the prospect of reading the unopened Herculaneum scrolls is deeply exciting. Charred in the explosion that devastated Herculaneum, the scrolls are too fragile to physically unroll. But researchers led by Brent Seales, a computer scientist at the University of Kentucky, showed that it’s not necessary. The team developed techniques to virtually unwrap CT scans of the scrolls and trained machine learning algorithms to detect ink on the warped and blackened pages, often detecting subtle changes in the papyrus fiber patterns.
The work gave rise to the Vesuvius Challenge, a competition backed by Silicon Valley entrepreneurs, with lucrative prizes for the team that deciphered the largest amount of text scanned from scroll fragments. In February, three computer science students shared the grand prize of $700,000 (£557,000) after reading hundreds of Greek words in 15 columns of the scroll. Dr. Federica Nicolardi, a papyrologist at the Federico II University of Naples, is studying one of the columns, in which Filodemo analyzes how perception engenders knowledge when images “collide with our sensory organs.”
The content of the remaining scrolls is up for debate. Some may be Latin texts. There could be Sappho’s poems, Mark Antony’s treatise on drunkenness, perhaps early writings on the Judeo-Christian tradition. Some of the scrolls are glued together, which could shed light on how ancient libraries were organized.
Nat Friedman, founding sponsor of the challenge, has announced a new series of prizes to encourage researchers to read 90% of a scroll by the end of this year. A major hurdle is the tedious “segmentation” process, which involves manually tracing the layers of the digital scroll so that the text-reading algorithm doesn’t mistake one warped layer for another. Work is underway to automate the process, which Friedman says will be a big step forward. “That should unlock lots and lots of text,” he said. In advance, Friedman has booked almost two weeks of air time at Diamond Light Source in Oxfordshire to scan potentially dozens more Herculaneum scrolls.
The new wave of technologies will shed light on more than just the Herculaneum scrolls. The same approach could read the papyrus wrapped around Egyptian mummies, with sheets ranging from letters to laundry lists. There are boxes of those things in the back rooms of museums.
Dr Thea Sommerschield, historian and epigrapher at the University of Nottingham, and her colleagues recently surveyed how machine learning is being applied to ancient languages. The tools, they concluded, are reshaping the field in the same way that the microscope and telescope transformed science.
Sommerschield and Yannis Assael of Google DeepMind are co-directors of a project called Ithaca, a transformer-based AI program, the technology behind ChatGPT. It is available to everyone and can predict missing characters in ancient Greek inscriptions and propose times and places where they may have occurred. The tool, which is used hundreds of times a week, promises to shed new light on the ancient world. Inscriptions on 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 insights into the thought, language, society and politics of the ancient world in general,” Sommerschield said.
So far, the best results come from multidisciplinary teams with computer engineers working alongside academics. These mixed teams were vital, Sommerschield said, as were efforts to create clean, well-curated data sets that cover not only ancient Greek and other popular languages, but also writings from around the world. “If we have that kind of interaction, then we will gain the trust, interest and commitment of computer scientists, the general public and academic communities,” she added.
