Get curated editors’ picks, peeks behind the scenes, film recommendations and more.
Ancient stone inscriptions offer some of the most powerful primary sources available to historians. However, as these stones are often many thousands of years old, and thus eroded, chipped or otherwise compromised, they can also be immensely difficult to translate, as well as to place in time and space. With this important challenge in mind, Thea Sommerschield, a historian, and Yannis Assael, an artificial intelligence research scientist, teamed up to create Ithaca – a deep neural network that helps to date, place and translate ancient text. Working from a database of 80,000 ancient Greek inscriptions, the neural network combines its sophisticated understanding of patterns to predict missing words and offer guesses as to when and where a text was written. Worth noting too that, while the program fills in the blanks much better than historians working independently of the technology, it was at its most accurate when collaborating with a human expert.
Video by Nature
Producer: Shamini Bundell
video
The ancient world
Petty squabbles and bloody battles – the life of an ancient Roman soldier
18 minutes
video
Astronomy
The remarkable innovations inspired by our need to know the night sky
5 minutes
video
Knowledge
Why it takes more than a lifetime to truly understand a single meadow
11 minutes
video
Physics
Groundbreaking visualisations show how the world of the nucleus gives rise to our own
10 minutes
video
War and peace
‘She is living on in many hearts’ – Otto Frank on the legacy of his daughter’s diary
12 minutes
video
Art
Why Diego Velázquez needed a lifetime to paint his enigmatic masterpiece
31 minutes
video
Earth science and climate
There’s a ‘climate bomb’ ticking beneath the Arctic ice. How can we prepare?
8 minutes
video
Political philosophy
The radical activist couple who fought for social change in the courtroom
21 minutes
video
Physics
To change the way you see the Moon, view it from the Sun’s perspective
5 minutes