CORDIS - Forschungsergebnisse der EU
CORDIS

Machine Learning for the Study of Ancient Epigraphic Cultures

Projektbeschreibung

Maschinelles Lernen für das Studium der epigraphischen Kulturen des antiken Mittelmeerraums

Das EU-finanzierte Projekt PythiaPlus wird das Wesen der epigraphischen Kulturen der griechischen und römischen Welt mithilfe der jüngsten Fortschritte in der künstlichen Intelligenz untersuchen. Inschriften liefern aus erster Hand Hinweise auf das Denken, die Sprache, die Gesellschaft und die Geschichte der Antike. Die Anzahl und Vielfalt dieser Dokumente machen das Studium von Nuancen und Verschiebungen zwischen Inschriften jedoch zu einer anspruchsvollen Aufgabe. PythiaPlus revolutioniert unsere Möglichkeiten des Datenzugriffs und der Datenanalyse durch die Implementierung von Modellen des maschinellen Lernens und wird die anhand dieser Modelle entdeckten epigraphischen Muster in den Texten und Metadaten von Tausenden griechischen und lateinischen Inschriften interpretieren und damit unser Verständnis der epigraphischen Kommunikation im antiken Mittelmeerraum verändern.

Ziel

PythiaPlus proposes to explore and interpret the nature of the epigraphic cultures of the ancient Mediterranean using Artificial Intelligence. Specifically, it will use Machine Learning (ML) models to trace distinctiveness and change in the Greek and Roman epigraphic evidence on an unprecedented large scale and in unparalleled detail, revealing new insights in linguistic and cultural interactions.
Inscriptions are primary evidence for reconstructing the history and thought of the ancient world, due to their large number and variety in content. However, the chronological development and regional diffusion of inscriptions are not uniform. No print or digital resources exist allowing a precise quantification of inscriptions by time and place, and current approaches are generally confined to specific languages or localised case studies. Recent advances in ML can overcome these limitations: ML is a field of Artificial Intelligence that allows statistical models to discover patterns in large datasets, and learn meaningful representations of them. Because such models can train over vast amounts of data, they can overcome the limitations in quantification and breadth of analysis of current resources and approaches.
By revolutionising our ability to access and analyse the epigraphic data through the implementation of advanced digital technologies, this research will enable and undertake the interpretation of the epigraphic patterns and parallels discovered by ML models across the texts and metadata of thousands of Greek and Latin inscriptions. PythiaPlus will transform our understanding of the use of epigraphic communication and the nature of cultural interference within the written and indirectly spoken languages of the ancient world, making a substantial contribution to the study of Epigraphy and the Historical Sciences.

Koordinator

UNIVERSITA CA' FOSCARI VENEZIA
Netto-EU-Beitrag
€ 171 473,28
Adresse
DORSODURO 3246
30123 Venezia
Italien

Auf der Karte ansehen

Region
Nord-Est Veneto Venezia
Aktivitätstyp
Higher or Secondary Education Establishments
Links
Gesamtkosten
€ 171 473,28