Latest news with #ancienttexts
The Independent
5 days ago
- Science
- The Independent
Google unveils AI that deciphers missing Latin words in ancient Roman inscriptions
Google 's DeepMind has unveiled a new artificial intelligence tool capable of deciphering and contextualising ancient texts, including Roman-era Latin inscriptions. The new AI, named Aeneas, could be a transformative tool that can assist historians expand our understanding of the past, the tech giant said on Thursday. A study published in the journal Nature demonstrated that Aeneas could predict missing parts of Latin inscriptions from the ancient Roman period. Even though writing was common in the Roman world, texts recovered by historians from the time period are often fragmentary, weathered, or defaced. Restoring and dating these texts is nearly impossible without contextual information and hence historians attempt to identify 'parallels' – which are texts with similarities in wording, syntax, standardised formulas or provenance. Aeneas can accelerate this contextualisation process, predict missing text, even when the length is uncertain, researchers say. 'It reasons across thousands of Latin inscriptions, retrieving textual and contextual parallels in seconds that allow historians to interpret and build upon the model's findings,' DeepMind said in a statement. 'Aeneas sets a new state-of-the-art benchmark in restoring damaged texts and predicting when and where they were written,' the AI firm said, adding that the tool also been developed to include visual imagery in its considerations. In the new study, scientists and historians launched a collaborative study to assess inscriptions dating from the seventh century BC to the eighth century AD. Historians found that the context suggestions provided by Aeneas were useful in 90 per cent of cases and improved their confidence in key tasks by 44 per cent. When historians worked with the AI model, they could see better results in restoration and geographical attribution tasks than when Aeneas or the scholars worked alone. The study found that the AI could date events within a 13-year time frame. Researchers hope the AI model can also be adapted to other ancient languages to decipher scripts from papyri to coinage, expanding its capabilities, and help draw connections across a wider range of historical evidence. Aeneas works by taking an inscription's text and image as input. Scientists trained the AI model using a 'large and reliable dataset' that draws from decades of work by historians to create digital collections, including EDR – a searchable resource that provides texts, bibliographic information, and descriptive data for Latin and Greek inscriptions from ancient Italy. Researchers organised these collections into a more accessible dataset of over 176,000 Latin inscriptions from across the ancient Roman world. After processing the text image of an inscription, the AI model relies on some of its specialised internal networks to restore characters and date the text, while geographical attribution also uses images of the inscriptions as input. Aeneas then contextualises the text by retrieving a list of parallels, creating a 'kind of historical fingerprint' of what the text says, its language, when and where it came from, and how it relates to other inscriptions, researchers explained. Scientists found that the AI could restore damaged inscriptions with an accuracy of 73 per cent in gaps of up to ten characters. When Aeneas assessed one of the most famous Roman inscriptions: the Res Gestae Divi Augusti – Emperor Augustus' first-person account of his achievements – it predicted two possible dates, one at around 10-1 BC and a more confident prediction of between 10 to 20 AD, much in line with a long-standing debate among historians. 'These findings are supported by the results of an extensive historian–AI evaluation, in which historians confirmed that Aeneas can seamlessly integrate into research workflows and provide a transformative aid for historical inquiry,' researchers wrote.
The Guardian
6 days ago
- Science
- The Guardian
Google develops AI tool that fills missing words in Roman inscriptions
In addition to sanitation, medicine, education, wine, public order, irrigation, roads, a freshwater system and public health, the Romans also produced a lot of inscriptions. Making sense of the ancient texts can be a slog for scholars, but a new artificial intelligence tool from Google DeepMind aims to ease the process. Named Aeneas after the mythical Trojan hero, the program predicts where and when inscriptions were made and makes suggestions where words are missing. Historians who put the program through its paces said it transformed their work by helping them identify similar inscriptions to those they were studying, a crucial step for setting the texts in context, and proposing words to fill the inevitable gaps in worn and damaged artefacts. 'Aeneas helps historians interpret, attribute and restore fragmentary Latin texts,' said Dr Thea Sommerschield, a historian at the University of Nottingham who developed Aeneas with the tech firm. 'That's the grand challenge that we set out to tackle.' Inscriptions are among the most important records of life in the ancient world. The most elaborate can cover monument walls, but many more take the form of decrees from emperors, political graffiti, love poems, business records, epitaphs on tombs and writings on everyday life. Scholars estimate that about 1,500 new inscriptions are found every year. 'What makes them unique is that they are written by the ancient people themselves across all social classes,' said Sommerschield. 'It's not just history written by the victors.' But there is a problem. The texts are often broken into pieces or so ravaged by time that parts are illegible. And many inscribed objects have been scattered over the years, making their origins uncertain. The Google team led by Yannis Assael worked with historians to create an AI tool that would aid the research process. The program is trained on an enormous database of nearly 200,000 known inscriptions, amounting to 16m characters. Aeneas takes text, and in some cases images, from the inscription being studied and draws on its training to build a list of related inscriptions from 7BC to 8AD. Rather than merely searching for similar words, the AI identifies and links inscriptions through deeper historical connections. Having trained on the rich collection of inscriptions, the AI can assign study texts to one of 62 Roman provinces and estimate when it was written to within 13 years. It also provides potential words to fill in any gaps, though this has only been tested on known inscriptions where text is blocked out. In a test run, researchers set Aeneas loose on a vast inscription carved into monuments around the Roman empire. The self-congratulatory Res Gestae Divi Augusti describes the life achievements of the first Roman emperor, Augustus. Aeneas came up with two potential dates for the work, either the first decade BC or between 10 and 20AD. The hedging echoes the debate among scholars who argue over the same dates. In another test, Aeneas analysed inscriptions on a votive altar from Mogontiacum, now Mainz in Germany, and revealed through subtle linguistic similarities how it had been influenced by an older votive altar in the region. 'Those were jaw-dropping moments for us,' said Sommerschield. Details are published in Nature and Aeneas is available to researchers online. In a collaboration, 23 historians used Aeneas to analyse Latin inscriptions. The context provided by the tool was helpful in 90% of cases. 'It promises to be transformative,' said Mary Beard, a professor of classics at the University of Cambridge. Jonathan Prag, a co-author and professor of ancient history at the University of Oxford, said Aeneas could be run on the existing corpus of inscriptions to see if the interpretations could be improved. He added that Aeneas would enable a wider range of people to work on the texts. 'The only way you can do it without a tool like this is by building up an enormous personal knowledge or having access to an enormous library,' he said. 'But you do need to be able to use it critically.'
The Guardian
6 days ago
- Science
- The Guardian
Google develops AI tool that fills missing words in Roman inscriptions
In addition to sanitation, medicine, education, wine, public order, irrigation, roads, a freshwater system and public health, the Romans also produced a lot of inscriptions. Making sense of the ancient texts can be a slog for scholars, but a new artificial intelligence tool from Google DeepMind aims to ease the process. Named Aeneas after the mythical Trojan hero, the program predicts where and when inscriptions were made and makes suggestions where words are missing. Historians who put the program through its paces said it transformed their work by helping them identify similar inscriptions to those they were studying, a crucial step for setting the texts in context, and proposing words to fill the inevitable gaps in worn and damaged artefacts. 'Aeneas helps historians interpret, attribute and restore fragmentary Latin texts,' said Dr Thea Sommerschield, a historian at the University of Nottingham who developed Aeneas with the tech firm. 'That's the grand challenge that we set out to tackle.' Inscriptions are among the most important records of life in the ancient world. The most elaborate can cover monument walls, but many more take the form of decrees from emperors, political graffiti, love poems, business records, epitaphs on tombs and writings on everyday life. Scholars estimate that about 1,500 new inscriptions are found every year. 'What makes them unique is that they are written by the ancient people themselves across all social classes,' said Sommerschield. 'It's not just history written by the victors.' But there is a problem. The texts are often broken into pieces or so ravaged by time that parts are illegible. And many inscribed objects have been scattered over the years, making their origins uncertain. The Google team led by Yannis Assael worked with historians to create an AI tool that would aid the research process. The program is trained on an enormous database of nearly 200,000 known inscriptions, amounting to 16m characters. Aeneas takes text, and in some cases images, from the inscription being studied and draws on its training to build a list of related inscriptions from 7BC to 8AD. Rather than merely searching for similar words, the AI identifies and links inscriptions through deeper historical connections. Having trained on the rich collection of inscriptions, the AI can assign study texts to one of 62 Roman provinces and estimate when it was written to within 13 years. It also provides potential words to fill in any gaps, though this has only been tested on known inscriptions where text is blocked out. In a test run, researchers set Aeneas loose on a vast inscription carved into monuments around the Roman empire. The self-congratulatory Res Gestae Divi Augusti describes the life achievements of the first Roman emperor, Augustus. Aeneas came up with two potential dates for the work, either the first decade BC or between 10 and 20AD. The hedging echoes the debate among scholars who argue over the same dates. In another test, Aeneas analysed inscriptions on a votive altar from Mogontiacum, now Mainz in Germany, and revealed through subtle linguistic similarities how it had been influenced by an older votive altar in the region. 'Those were jaw-dropping moments for us,' said Sommerschield. Details are published in Nature and Aeneas is available to researchers online. In a collaboration, 23 historians used Aeneas to analyse Latin inscriptions. The context provided by the tool was helpful in 90% of cases. 'It promises to be transformative,' said Mary Beard, a professor of classics at the University of Cambridge. Jonathan Prag, a co-author and professor of ancient history at the University of Oxford, said Aeneas could be run on the existing corpus of inscriptions to see if the interpretations could be improved. He added that Aeneas would enable a wider range of people to work on the texts. 'The only way you can do it without a tool like this is by building up an enormous personal knowledge or having access to an enormous library,' he said. 'But you do need to be able to use it critically.'
Gizmodo
06-05-2025
- Science
- Gizmodo
AI Identifies Author of Charred Scroll Buried by Vesuvius for 2,000 Years
For the first time, researchers have identified the author and title of a document that's been locked inside a charred scroll for nearly 2,000 years—without peeling back a single layer. The scroll, PHerc. 172, was recovered from the ruins of Herculaneum, the ancient Roman town buried by the ash and debris of Mount Vesuvius in 79 CE. The scroll is one of three Herculaneum scrolls that now reside at Oxford's Bodleian Libraries. Thanks to high-resolution scans and some seriously clever machine learning, scholars were able to virtually 'unwrap' the papyrus and read the name inside: On Vices, by the Epicurean philosopher Philodemus. The treatise—its full name being On Vices and Their Opposite Virtues and In Whom They Are and About What, according to Fine Books Magazine, is basically ancient self-help, exploring how to live a virtuous life by avoiding vice. Philodemus wrote the work in the first century BCE and it is now being read for the first time since it was buried in the devastating volcanic eruption nearly 2,000 years ago. The discovery—confirmed by multiple research teams—earned the project's collaborators the $60,000 First Title Prize from the Vesuvius Challenge, an open-science competition that's been making ancient texts readable using AI. In recent years, artificial intelligence has been instrumental in deciphering the ancient, carbonized scrolls from Herculaneum, a Roman town buried by the eruption of Mount Vesuvius in 79. These scrolls, first discovered in the 18th century in what is now known as the Villa of the Papyri, comprise one of the only surviving libraries from the classical world. Due to their fragile, charred condition, traditional (read: manual) methods of unrolling the scrolls often destroyed them. Now, researchers are using advanced imaging and machine learning to read these texts without ever opening them. The turning point came in 2015, when scientists used X-ray tomography to read a different ancient scroll from En-Gedi, creating a 3D scan that could be virtually 'unwrapped.' Building on this, researchers at the University of Kentucky developed the Volume Cartographer, a program that uses micro-CT imaging to detect the faint traces of carbon-based ink on the scrolls. Because the ink contains no metal, unlike many ancient writing materials, a neural network had to be trained to recognize subtle patterns indicating ink on the carbonized papyrus. In 2019, researchers successfully demonstrated this technique, setting the stage for broader applications. These breakthroughs culminated in the Vesuvius Challenge, launched in 2023 to crowdsource the decoding of unopened scrolls. Participants use AI tools—particularly convolutional neural networks and transformer models—to identify and reconstruct text within the scrolls. In October 2023, the first word ('purple') was read from an unopened scroll, earning a $40,000 prize. The challenge continues, with prizes offered for deciphering additional text and improving the technology. Brent Seales, a computer scientist at the University of Kentucky and co-founder of the Vesuvius Challenge, told The Guardian that the team's current bottleneck is cleaning, organizing, and enhancing the scan data so that researchers can actually interpret the carbonized ink as text. Importantly, the digital unwrapping process is guided by human expertise. AI highlights likely areas of ink on the ancient documents, but scholars interpret the patterns to determine if they form coherent words or phrases. The goal is not only to recover lost philosophical texts, many of which are possibly by Epicurus or his followers, but also to establish a scalable system for digitizing and decoding ancient texts—transforming our understanding of the classical world.
