Hybrid Ontology and NLP-Based Annotation Model for Indigenous Lexicon and Folklore Preservation
Durdona Khudayberganova, Nilufar Tosheva, Hafiza Aslanova, Olim Kayumov, Халлиева Гулноз Искандаровна, Otabek Mukhitdinov, Ibrokhim B. Sapaev, Dilfuza Tursunova · Indian Journal of Information Sources and Services · 2025
This model combines an ontology with NLPtechnology to aid in retaining Indigenous vocabularies andfolklore aimed at low-resource languages. Automatic annotationand classification of culture-specific narratives is achievedthrough semantic web technologies and natural languageprocessing. Contextual intricacies are preserved culturally andcontextually. The model contains a folklore ontology annotatedwith the aid of community and expert volunteers, therebyensuring relevancy and accuracy. Case studies on the Uzbeklanguages showed enhanced digitization, increased accessibility,and the semantic understanding of indigenous ontologicalknowledge. The study also highlighted contextual digitalpreservation addressing resource sensitivity, rare dialectalvariation, and culture-informed context preservation. Futurework includes broadening the Corpora, optimizing the modelsfor specific dialects, and establishing ethical frameworks forcommunity-centric preservation initiatives. This will helpresolve concerns about erasing indigenous knowledge whiledeveloping avenues for research on digital heritagepreservation.