This artificial intelligence completes the old damaged inscriptions

The study of history is one of the most complicated fields one can find. They must not only prepare themselves professionally to study cultures and languages ​​that are often no longer traced; but many of the sources they need damaged beyond repair. However, a powerful new tool has emerged in Ithaca, and it is an artificial intelligence with the power of DeepMind that manages to change the course of history.

As described from TechCrunch, this AI is able to guess lost or hard-to-understand words due to wear and tear with amazing accuracy. Also as can interpret approximate location and date of text. Of course, this is a use that is at least different from that usually given to artificial intelligences; but it shows how useful this technology can be in whatever area we prepare it for.

The problem of wear and tear in ancient texts affects many disciplines that study historical elements. Many experts and academics work with gradient materials By the time. Among them we have stone, clay or papyrus. Moreover, these writings can be in Akkadian, Ancient Greek, Linear A, and can talk about anything; from a hero’s journey to a daily report. However, they all have in common great damage accumulated by the passage of millennia.

What does this artificial intelligence do

artificial intelligence, now called Ithaca, showed surprisingly high accuracy. Allows you to fill in gaps in worn or missing text. According to the aforementioned medium’s comments, these spaces “can be as short as a lost letter or as long as a chapter”.

Egyptian hieroglyphs

Gaps where text is worn or torn are often called gaps, and they can be as short as a missing letter or as long as a chapter or even an entire story. Completing them may be trivial or impossible, but you have to start somewhere, and that’s where Ithaca aims to help.

Ithaca was formed with an entire library of ancient Greek texts. Moreover, its creators named it after the native island of Odysseus. Ithaca has the ability to retrieve missing words or phrases as they were probably written. It is so efficient that it can even determine when these stories were written, and even where. Sure, it’s not going to fill entire lost pages, but it’s a great tool that expands team possibilities research that works with these very old texts.

Image by DeepMind

Ithaca, the future of historical studies

Ithaca illustrates the potential contribution of natural language processing and machine learning in the humanities.

We need more projects like Ithaca to continue to show this potential, but also adequate courses and teaching materials to train future researchers, who will have a better joint understanding of human sciences and AI methods.

Ion Androutsopoulos, professor at the University of Athens

the specialist journal Nature published the results of its effectiveness. For it, took as an example the decrees of decline of Athens. Until then, these texts were thought to have been created on dates around the year 445 BC. however, Ithaca’s suggestions they throw that they were written in the year 420 BC. about. This result is the same as the most recent tests carried out by experts.

Of course, this artificial intelligence still has a long way to go before it is completely reliable. According to the experts of the study, Ithaca achieved a total of 25% reliability on the first scan. However, by coupling AI efforts with human knowledge, academics achieved up to 72% accuracy. Of course, this is one of those situations where human perception is essential to the process; but without a doubt Ítaca has been a great help in speeding up processes, eliminating details and suggesting starting points.