Ancient history relies on disciplines such as epigraphy—the study of inscribed texts known as inscriptions—for evidence of the thought, language, society and history of past civilizations1. 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.
Creating some regular releases of the data, from this point forward.
The project EpiCUM (Epigraphs of Castello Ursino Museum) pursued the important objective of valorizing and making publicly available (in digital format) the 574 epigraphs of the Castello Ursino Museum in Catania. The various phases of the project (cataloguing and examination of the epigraphic material; setting-up of an exhibition; organization of an international scientific conference; encoding according to the EpiDoc schema; creation of a digital scientific edition; realization of a web platform) seen the involvement of different entities, among which, in particular, a group of students of a High School. Their activities represented a good example of work-related learning.
The paper presents the corpus of the Inscriptions of Georgia, a result of a PhD research project at the Ilia State University, Tbilisi, Georgia. The database, built using the EpiDoc Front-End Services (EFES) platform, combines the EpiDoc editions of hundreds of inscriptions unearthed in Georgia, and published in print during the 18th-20th centuries. The paper outlines the main issues addressed during the creation of the database and the encoding of the inscriptions. It illustrates the core features of the corpus, with an emphasis on the advantages of the digital edition of the epigraphic monuments with the TEI-EpiDoc standard and the EFES platform.
This essay describes and traces the development of »Inscriptions of Israel/ Palestine,« a website devoted to collecting, making freely accessible, and analyzing ancient inscriptions from the region of modern Israel/Palestine. The essay pays special attention to some of the more important decisions that we have made and our rationale behind them. One of the primary goals of this essay is to introduce the process that we have used and the challenges that we have confronted (and continue to confront) to scholars who are involved in or contemplating starting their own digital humanities projects. At the end, I reflect more broadly on how what we have learned might contribute to the development of digital humanities in the area of Jewish studies.