We introduce the first model for contextualizing ancient inscriptions, designed to help historians better interpret, attribute, and recover fragmentary texts.
Writing was everywhere in the Roman world, inscribed on everything from imperial monuments to everyday objects. From political graffiti, love poems, and epitaphs to business deals, birthday invitations, and magical spells, inscriptions provide modern historians with a rich insight into the diversity of everyday life in the Roman world.
Often these texts are fragmentary, weathered, or intentionally defaced. Without contextual information, it is nearly impossible to reconstruct, date, and place them, especially when comparing similar inscriptions.
Today, we publish a paper in Nature introducing Aeneas, the first artificial intelligence (AI) model for contextualizing ancient inscriptions.
When dealing with ancient inscriptions, historians traditionally rely on specialized knowledge and specialized resources to identify “similarities.” Similarities are documents that share similarities in wording, syntax, standardized formulas, provenance, etc.
Aeneas greatly accelerates this complex and time-consuming task. Reasons through thousands of Latin inscriptions, searches for textual and contextual similarities in seconds, and enables historians to interpret and build on models of discovery.
