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
Physics
The abyss at the edge of human understanding – a voyage into a black hole
4 minutes
video
Film and visual culture
‘Bags here are rarely innocent’ – how filmmakers work around censorship in Iran
8 minutes
video
Language and linguistics
Closed captions suck. Here’s one artist’s inventive project to make them better
8 minutes
video
Thinkers and theories
A rare female scholar of the Roman Empire, Hypatia lived and died as a secular voice
5 minutes
video
Anthropology
Why are witchcraft accusations so common across human societies?
4 minutes
video
Wellbeing
Born in China, Zee seeks a gender-affirming life in the American Midwest
11 minutes
video
Chemistry
Why do the building blocks of life possess a mysterious symmetry?
12 minutes
video
Rituals and celebrations
A whale hunt is an act of prayer for an Inuit community north of the Arctic Circle
8 minutes
video
Cosmology
Tiny, entangled universes that form or fizzle out – a theory of the quantum multiverse
11 minutes