This website does readability filtering of other pages. All styles, scripts, forms and ads are stripped. If you want your website excluded or have other feedback, use this form.

DeepMind AI beats humans at deciphering damaged ancient Greek tablets | New Scientist

×

THE DAILY NEWSLETTER

Sign up to our daily email newsletter

Subscribe and save Forgotten Password?

Sign up for free|Educational access

Sign up for more online articles

A selection of top articles hand-picked by our editors available only to registered users.

Get increased access now

Manage your subscription

Check your subscription package, update your details, renew or upgrade.

Manage your subscription here

Activate subscription

DeepMind AI beats humans at deciphering damaged ancient Greek tablets

Technology 18 October 2019

By Gege Li

A Greek text inscription on a rock in Delphi

Teefa/Getty Images

Artificial intelligence is learning to decipher damaged ancient Greek engravings. The AI seems to be better than humans at filling in missing words, but may be most useful as a collaborative tool, where researchers use it to narrow down the options.

There are thousands of ancient inscriptions we already know about, with dozens more discovered every year. Unfortunately, many have become eroded or damaged over the centuries, resulting in segments of text being lost. Figuring out what the gaps could be is a difficult task, involving looking at the rest of the inscription and other similar texts.

Yannis Assael at DeepMind and his colleagues trained a neural network, a type of AI algorithm, to guess missing words or characters from Greek inscriptions, on surfaces including stone, ceramic and metal, that were between 1500 and 2600 years old.

Advertisement

The AI, called Pythia, learned to recognise patterns in 35,000 relics, containing more than 3 million words. The patterns it picks up on include the context in which different words appear, the grammar, and also the shape and layout of the inscriptions.

Given an inscription with missing information, Pythia provides 20 different suggestions that could plug the gap, with the idea that someone could then select the best one using their own judgement and subject knowledge. “It’s all about how we can help the experts,” says Assael.

Read more: Mind meld: Artificial intelligence is improving the way humans think

To test the system, the team hid nine letters of a Greek personal name from Pythia. It managed to fill in the blanks. In a head-to-head test, where the AI attempted to fill the gaps in 2949 damaged inscriptions, human experts made 30 per cent more mistakes than the AI. Whereas the experts took 2 hours to get through 50 inscriptions, Pythia gave its guesses for the entire cohort in seconds.

This shows the potential of AI-assisted restoration, says Thea Sommerschield at the University of Oxford, who was part of the team. “The reward is huge because it tells us about almost every aspect of the religion, social and economic life of the ancient world,” she says.

Philippa Steele at the University of Cambridge agrees that Pythia could assist restoration efforts, although humans would still be needed to put the pieces together by eye and then decipher them before this could happen.

“It looks to me as though the highest success rates would be achieved when… we are just missing small parts of a long text, or when there are plenty of similar parallels for a newly discovered fragmentary text,” she says.

Reference: arXiv, arxiv.org/abs/1910.06262

More on these topics:

Advertisement
  1. Exclusive: Humans placed in suspended animation for the first time
  2. Why the line between life and death is now more blurred than ever
  3. Don’t miss: Art meets science, atoms find love and numbers grow curves
  4. Palm oil from Colombia is more climate and wildlife friendly
  5. What hypnosis does to your brain, and how it can improve your health
  1. Controversial DNA screening technique used for at least one pregnancy
  2. The mystery of the mass of the neutrino could soon be solved
  3. An AI doctor is analysing heart scans in dozens of hospitals
  4. Swarms of golf ball-sized robots could detect leaks in the sewers
  5. Why almost everyone believes in an afterlife – even atheists
  1. Blue Planet II’s Steve Simpson explores the sounds of the ocean
  2. Mixed reality in military aircraft of the future
  3. How the young can rejuvenate the old
  4. Skeletons: the frame of life
  5. The delightful and dangerous world of liquids
  1. Controversial DNA screening technique used for at least one pregnancy
  2. The mystery of the mass of the neutrino could soon be solved
  3. Swarms of golf ball-sized robots could detect leaks in the sewers
  4. Elon Musk unveils Tesla's 'cybertruck' – an electric pickup truck
  5. Humans across cultures may share the same universal musical grammar