Scientists at the University of Chicago have developed a machine learning system that can automatically translate texts on ancient clay tablets.
According to The University of Chicago News, the DeepScribe system will initially be used to decipher the cuneiform script used in the ancient Iranian Achaemenid Empire (550-330 BC).
Existing computer systems experience certain difficulties in translating such texts due to the complexity of the symbols and the three-dimensional shape of the plates on which they are written. According to researchers from the University of Chicago, their system is able to cope with the task.
More than 6, 000 annotated images of texts of that time are used to create a model as a "simulator". Their complete decoding will provide information about the history, society and language of the Achaemenids. The training is based on the Achaemenid language dictionary, which contains over 100, 000 individual characters.
Sanjay Krishnan, a computer science professor at the University of Chicago, used this annotated kit to teach AI to read other, as yet unknown tablets. As a result, the system was able to decipher the characters contained in them with 80% accuracy.