PYTHIA: Machine learning for epigraphic text restoration

Digital Classicist London Seminar 2020

Thea Sommerschield (Oxford), PYTHIA: a deep neural network model for the automatic restoration of ancient Greek inscriptions

Fri, Jun 5, 2020, 17:30 (UK time)
Institute of Classical Studies, University of London
Online seminar, streamed live and archived at:

Ancient History relies on Epigraphy, the study of ancient inscribed texts (called “inscriptions”), for evidence of the recorded past. However, inscriptions are often damaged over the centuries, and illegible parts of the text must be restored by epigraphists. PYTHIA is the first ancient text restoration model that recovers missing characters from a damaged text input using deep neural networks. Its architecture is carefully designed to handle long-term context information, and deal efficiently with missing or corrupted character and word representations. Th. Sommerschield will present this research, give examples of PYTHIA at work, and demonstrate how to use the model for personal research.

Μόνιμος σύνδεσμος σε αυτό το άρθρο: