Restoring and attributing ancient texts using deep neural networks

Восстановление и атрибуция древних текстов с помощью глубоких нейронных сетей
Yannis Assael, Ion Androutsopoulos, John Pavlopoulos, Nando de Freitas, Thea Sommerschield, Brendan Shillingford, Mahyar Bordbar, Marita Chatzipanagiotou, JONATHAN R. W. PRAG
2022-03-09

Ithacaancient Greek inscriptionsdeep neural networksgeographical attributiontextual restoration
. However, over the centuries, many inscriptions have been damaged to the point of illegibility, transported far from their original location and their date of writing is steeped in uncertainty. Here we present Ithaca, a deep neural network for the textual restoration, geographical attribution and chronological attribution of ancient Greek inscriptions. Ithaca is designed to assist and expand the historian's workflow. The architecture of Ithaca focuses on collaboration, decision support and interpretability. While Ithaca alone achieves 62% accuracy when restoring damaged texts, the use of Ithaca by historians improved their accuracy from 25% to 72%, confirming the synergistic effect of this research tool. Ithaca can attribute inscriptions to their original location with an accuracy of 71% and can date them to less than 30 years of their ground-truth ranges, redating key texts of Classical Athens and contributing to topical debates in ancient history. This research shows how models such as Ithaca can unlock the cooperative potential between artificial intelligence and historians, transformationally impacting the way that we study and write about one of the most important periods in human history.
1
Ithaca alone restores damaged texts with 62% accuracy, while historians using it improve their restoration accuracy from 25% to 72%.
2
Ithaca dates inscriptions to within 30 years of their ground-truth ranges and supports the redating of key Classical Athenian texts.
3
Ithaca is a deep neural network designed to restore damaged ancient Greek inscriptions and infer their geographic and chronological origins.
4
The model attributes inscriptions to their original locations with 71% accuracy.
5
The system emphasizes collaboration, decision support, and interpretability, demonstrating synergistic potential between artificial intelligence and historians.

ancient Greek inscriptions

textual restoration, geographical attribution, and chronological attribution of damaged or displaced inscriptions

Publication Details
Publication Date
2022-03-09
Journal
Publisher
ISSN
Cited by
265
Access Type
Author Information
Authors
Yannis Assael
Ion Androutsopoulos
John Pavlopoulos
Nando de Freitas
Thea Sommerschield
Brendan Shillingford
Mahyar Bordbar
Marita Chatzipanagiotou
JONATHAN R. W. PRAG
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%