Ancient Greek historians have now an artificial intelligence (AI) tool to help decipher texts.
Being a scholar in ancient Greek is difficult. The primary texts, on stone that may have been chipped and weathered through time, are frequently damaged beyond repair and hard to decipher, but a recent tool by Google’s DeepMind hopes to solve that using artificial intelligence.
The application is rather unusual because it uses AI, in a useful way outside of the technology world. DeepMind’s Ithaca, a machine learning model, makes surprisingly accurate guesses at missing words and the location and dates of ancient Greek texts.
Damaged ancient Greek texts deciphered using AI
Incomplete ancient texts have many problems, including degraded materials. The original document might be made of stone, clay or papyrus, written in Akkadian, ancient Greek or Linear A, and describe anything from a grocer’s bill to a hero’s journey. What ties them all together, though, is the damage accumulated over thousands of years.
Gaps, where the text is worn or torn off, are often called lacunae. The lacunae can be as short as a missing letter, as long as a chapter, or indeed an entire story. Filling them in can be easy or impossible — and that’s where Ithaca is meant to help.
AI to be used as a tool, not a solution
Used in a huge library of ancient Greek texts, Ithaca, which is named after Odysseus’ home island, not only can say what a missing word or phrase is likely to be, but can also take a shot at how old it is and where it was written. It’s not going to fill in a whole epic cycle on its own; it’s meant to be a tool for those who work with these texts, not a solution.
The study, published in the journal Nature, demonstrates its efficacy, using as an example some decrees from Periclean Athens. Thought to have been written in around 445 BC, Ithaca suggested that, based on its textual analysis, they were actually from 420 BC, which is in line with more recent evidence.
As for the text itself, experts in the study got about 25% accurate on the first pass, which is not exactly stellar, but text restoration is a long-term, not a short-term, project.
When paired with Ithaca, the experts achieved 72% accuracy, which is the perfect example of a situation in which humans were ultimately more accurate, but still, they can speed up their process by quickly eliminating dead ends or suggesting a starting point using AI.
You can test out a pared-down version of Ithaca, if you have some lacunae-ridden ancient Greek text handy, or use one of their provided examples to see how it fills in requested gaps. For longer pieces or if more than 10 letters missing, try it out in a Colab notebook, or download its code on its GitHub page.
Though ancient Greek is an obvious and fruitful area for Ithaca to start, the team is already hard at work on other languages — Akkadian, Demotic, Hebrew, and Mayan — as well. And more will be added over time.
“Ithaca illustrates the potential contribution of natural language processing and machine learning in the humanities,” said Ion Androutsopoulos, a professor at Athens University who worked on the project.
“We need more projects like Ithaca to further showcase this potential, but also suitable courses and teaching material to educate future researchers who will have a better joint understanding of both the humanities and AI methods.”