The software artificialintelligence can help historians interpret and date ancient texts by reconstructing works that have been destroyed over time, according to a study published in Nature.
A team of computer scientists and classical studies experts led by DeepMind and Ca' Foscari University of Venice trained a neural network to be able to restore inscriptions written in ancient Greek between the 7th century B.C. and 5th century AD
The model, named Ithaca, can also estimate when the text was written and where it might have come from. Thus researchers can recover texts present on broken ceramic comeyea, or obscure texts found in various inscriptions.
First, the text should be transcribed by scanning an image of an old object. It is then fed to Ithaca for analysis. Works by predicting lost or blurred characters and restores words. The software creates and ranks a list of its top predictions. Archaeologists can then read them and judge whether the model's predictions are accurate or not.
Of course they are better achieved Results με την συνεργασία ανθρώπου και μηχανής. Τότε που οι αρχαιολόγοι δούλευαν μόνοι τους, ήταν 25 τοις εκατό ακριβείς στο να συνδυάζουν αρχαία κείμενα. Σε συνεργασία με το Ithaca το επίπεδο ακρίβειας ανέβηκε στο 72 τοις εκατό. Η απόδοση του μοντέλου μηχανικής εκμάθησης από μόνη της είναι περίπου 62 τοις εκατό ακριβείς. Μπορεί επίσης να εντοπίσει με ακρίβεια 71 τοις εκατό την τοποθεσίας που γράφτηκε το κείμενο και μπορεί να χρονολογήσει τα έργα με απόκλιση 30 ετών από τη creation between 800 BC and 800 AD
Ithaca trained on more than 63.000 Greek inscriptions containing more than three million words from the Packard Humanities Institute's Searchable Greek Inscriptions repositories. The team filled in parts of the text and instructed the model to fill in the blanks.
Google's DeepMind is now adapting its model to other types of ancient writing systems, such as Akkadian developed in Mesopotamia, language of ancient Egypt, the Mayan language from Central America and ancient Hebrew.
Inscriptions