📜 Edge#174: How DeepMind Uses Transformer Models to Help Restore Ancient Inscriptions

Ithaca is a transformer based architecture used to help historians restore ancient Greek text

On Thursdays, we do deep dives into one of the freshest research papers or technology frameworks that is worth your attention. Our goal is to keep you up to date with new developments in AI to complement the concepts we debate in other editions of our newsletter.

💥 What’s New in AI: How DeepMind Uses Transformer Models to Help Restore Ancient Inscriptions

Epigraphy, or the study of ancient inscriptions, has been a cornerstone of our understanding of past civilizations. A huge part of epigraphy has been devoted to restoring ancient inscriptions. This process is highly challenging because many of those inscriptions are damaged, missing text, or using symbolic representations that are not fully understood. Last week, DeepMind published a research paper detailing their work on Ithaca, a transformer-based neural network that can help restore missing text from damaged inscriptions.

Named after the mythic Island depicted in Homer’s Odyssey, Ithaca focuses on