Developing a Standardised Vocabulary for Ukrainian Epigraphy and Expanding Digital Epigraphic Resources

Hamest Tamrazyan, Emanuela Boros, Frédéric Kaplan

Abstract: This paper addresses the lack of Ukrainian representation in digital epigraphy by developing a standardised vocabulary for Ukrainian inscriptions\(^{1}\). While existing projects like the electronic archive of Greek and Latin epigraphy (EAGLE) have comprehensive vocabularies for Greco-Roman artifacts, Ukrainian remains absent. By expanding the EAGLE vocabulary, we propose integrating Ukrainian terms into the framework. We also build a named entity recognition (NER) corpus for Ukrainian epigraphic inscriptions, train specialised NER models, and apply them to a larger corpus to discover new terms. This first step in building this vocabulary will further enable cross-lingual referencing of Ukrainian epigraphic data, enriching the digital humanities (DH) landscape while fostering broader academic collaboration and resource sharing.\(^{1}\)An example is presented Fig. 1.