Tamrazyan, HamestBoros, EmanuelaCampana, StefanoFerdani, DanieleGraf, HolgerGuidi, GabrieleHegarty, ZackaryPescarin, SofiaRemondino, Fabio2025-09-052025-09-052025978-3-03868-277-6https://doi.org/10.2312/dh.20253226https://diglib.eg.org/handle/10.2312/dh20253226This paper presents a corpus-based methodology for developing SKOS vocabularies tailored to Ukrainian epigraphy. Grounded in local academic traditions, the framework focuses on three domains: Inscriptions, Types of Inscriptions, and Execution Techniques. Terms were extracted using NLP tools and analyzed through a form/content/function and material/tool/method model. While the vocabulary is still in development, the classification framework is complete. It reflects regional epistemologies while ensuring interoperability with FAIR and EAGLE ontologies. This project contributes to digital heritage practices by promoting culturally sensitive, scalable classification of inscriptions from conflict-affected or historically marginalized contexts.Attribution 4.0 International LicenseCCS Concepts: Information systems → Ontologies; Digital libraries and archives; Computing methodologies → Natural language processing; Applied computing → Document metadata; Theory of computation → Semantics and reasoningInformation systems → OntologiesDigital libraries and archivesComputing methodologies → Natural language processingApplied computing → Document metadataTheory of computation → Semantics and reasoningCorpus-Based SKOS Development for Underrepresented and Endangered Ukrainian Epigraphic Heritage10.2312/dh.202532265 pages