AI Fills In The Missing Gaps From Ancient Greece

At some point during the 5th century BC ancient Athens embraced a more aggressive foreign policy. The tributes demanded from allies grew larger, military actions against those who revolted more vicious. For decades historians have argued over whether it was the great general Pericles or a successor who oversaw this shift. 

Now, Artificial Intelligence (AI) has entered the debate and could bring ancient texts back to life. Researchers have developed an Artificial Intelligence (AI) model which deciphered texts missing from ancient Greek inscriptions and has even dated them, helping historians decipher ancient text. 

Ancient history relies on disciplines such as epigraphy, the study of inscribed texts known as inscriptions for evidence of the thought, language, society and history of past civilisations. However, over the centuries, many inscriptions have been damaged to the point of illegibility, transported far from their original location and their date of writing is steeped in uncertainty. 

AI is transforming many areas of research, and a new AI tool helps to fill in missing text and estimate the time-frame and geographical origin of ancient inscriptions. A system created by DeepMind has been “trained” to analyse decrees from the ancient Athenian empire.

These written records, carved in stone, reflect decisions made by the leaders of Athens but are often damaged. The team of AI researchers at DeepMind, working with colleagues from the University of Venice, the University of Oxford and Athens University of Economics and Business, has developed an AI application to help historians fill in the gaps of text missing from stone, metal or pottery artefacts. 

These AI and Machine Learning techniques are providing new tools that could help archaeologists understand the past, particularly when it comes to deciphering ancient texts.

DeepMind’s AI model not only restore text that is missing from ancient Greek inscriptions but offers suggestions for when the text was written, within a 30-year period, and its possible geographic origins. “Inscriptions are really important because they are direct sources of evidence ... written directly by ancient people themselves,” Thea Sommerschield, a distinguished historian and machine learning expert who has helped created the model, told journalists in a press briefing.

And new software, named Ithaca, is trained on a dataset of some 78,608 ancient Greek inscriptions, each of which is labelled with metadata describing where and when it was written, to the best of historians’ knowledge. Like all Machine Learning systems, Ithaca looks for patterns in this information, encoding this information in complex mathematical models, and uses these inferences to suggest text, date, and origins.

Nature:    Greek Reporter:    The Times:    The Verge:    TechXplore:    Techcrunch:    TRT:     

You Might Also Read:

Using Artificial Intelligence To Fight Cancer: