Artificial intelligence is getting used to translate ancient clay cuneiform tablets that would give us clues to the origins of human civilisation.
The tech tools are in a position to decipher and reconstruct fragments Hittite texts in a fraction of the time it has taken humans to read and translate them.
Within the three millennia before the Common Era, advanced civilisations within the Near East recorded information on clay tablets using cuneiform – a writing system during which wedge-shaped symbols were pressed into wet clay with a stylus before being dried.
The project, developed by researchers on the University of Würzburg and the Academy of Sciences and Literature Mainz, focuses on cuneiform tablets produced around 3,500 years ago in what’s now Anatolia, in Turkey.
A lot of those tablets have since broken apart, with fragments dispersed across museums worldwide.
Scholars in Ancient Near Eastern Studies have long faced the challenge of reassembling the pieces in an effort to get well complete texts and gain insights into life in the traditional world.
The Würzburg-Mainz research team has spent years developing digital tools to support that work, particularly within the study of the Hittites.
Enroll for all of the newest stories
Start your day informed with Metro’s News Updates newsletter or get Breaking News alerts the moment it happens.
Their cuneiform system was highly complex, containing 375 signs representing each syllables and full words.
The group had already created the Hethitologie-Portal Mainz, an internet catalogue containing all 30,000 known Hittite clay tablet fragments, alongside research materials and texts.
A decade ago, the team also introduced a digital system able to capturing the unique three-dimensional characteristics of cuneiform signs, helping researchers reconstruct tablets with computer assistance.
In 2023, one other tool, TLHdig, enabled searches in cuneiform script and transliteration.
The newest development, often known as ‘Palaeographicum’, analyses digitised images from the Hethitologie-Portal and searches the gathering for similarly written signs. It could isolate individual characters and organise them into image tables for comparison.
Researchers currently have access to 70,000 photographs documenting greater than five million cuneiform characters. They are saying that the precise form of every sign is crucial since it reveals the distinctive handwriting kinds of individual scribes.
Although cuneiform was impressed into clay fairly than written with ink, personal styles are still visible. Some scribes drew the stylus away sharply, leaving flourishes, while others spaced their signs in recognisable ways.
‘With the naked eye, we are able to normally only do that slowly and with difficulty,’ said Professor Gerfrid Müller, an authority in Ancient Near Eastern Studies, adding that the three-dimensional nature of cuneiform often makes signs difficult to read in photographs.
‘The Palaeographicum is radically changing our work; it allows us to avoid wasting 1000’s of hours,’ said Professor Daniel Schwemer, head of the Department of Ancient Near Eastern Studies on the University of Würzburg.
He revealed that a comparison of handwriting across five clay tablet fragments, which once took three days, could now be accomplished in five minutes.
Researchers also imagine the tool could help date fragments more accurately. Since Hittite tablets rarely include dates, scholars depend on changes in handwriting styles over time – a field often known as palaeography – to estimate when texts were produced.
Nonetheless, the AI system remains to be being refined.
‘We’re repeatedly retraining the AI,’ said Professor Müller, adding that user feedback would shape future updates where technically feasible.
In keeping with the team, the international Hittitology community has already responded enthusiastically to the tool.
‘All researchers in Hittitology open the portal very first thing within the morning; they simply can’t do without it,’ said Professor Schwemer.
The researchers’ longer-term ambition is to coach the AI to discover the handwriting of individual scribes routinely.
They are saying the duty is difficult because scribes adapted their handwriting to different circumstances, producing more careful script in calm conditions and faster, less formal writing when drafting reports in the sphere.
‘If we achieve this goal, we could gain a greater picture of what individual scribes produced over the course of their skilled careers,’ Professor Schwemer said. “And we could compile a social history of Hittite writing culture.”
The foundations for the project were laid between 2018 and 2023 through the DFG-funded CuKa project, which developed the AI model underpinning Palaeographicum.
MORE: Birmingham city centre looks awful after ‘shameful eyesore’ tarmac replaces slabs
MORE: Human stays and burial offerings present in tombs under 1,800 12 months old pre-Aztec village in Mexico
MORE: Recent DNA evaluation raises fresh questions on Christopher Columbus’ origins