Today, Google DeepMind is introducing Aeneas, the first AI model for contextualizing ancient inscriptions, as detailed in a new paper in Nature.

This new generative AI model helps historians interpret, attribute and restore fragmentary ancient texts, enabling them to discover new insights into our past. Aeneas can search for parallels (texts that share similarities in wording, syntax, standardized formulas or provenance) across thousands of Latin inscriptions, process multimodal input (text and images) and restore gaps in text, setting a new state-of-the-art benchmark in the field.

While trained for Latin, Aeneas can be adapted to other ancient languages, scripts and media, from papyri to coinage. An interactive version of Aeneas is freely available to researchers, students and educators at predictingthepast.com, and its code and dataset are open source. Learn more about Aeneas on the Google DeepMind blog.