An Integrated Digitization and Validation Framework for Bessarabian Folklore Corpora Printed in Soviet Moldavian Cyrillic Script
Computer Science Journal of Moldova · 2026-11 · 34 (2) · 216-232
DOI: 10.56415/csjm.v34.10 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Science Journal of Moldova, 2026-11. Verfasst von Svetlana Cojocaru und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
This paper proposes a framework for constructing a clean and linguistically enriched corpus, FolkAI, of Bessarabian folklore from texts printed in Soviet Moldavian Cyrillic. The starting data are Cyrillic OCR texts obtained through previous digitization work with the HeDy platform. The present contribution concerns subsequent text processing: OCR-oriented cleanup, dehyphenation, transliteration, word-list generation, lexical filtering, contextual inspection, and human validation. A local Windows/Python pipeline combines Dexonline and Hunspell resources to identify candidate non-standard or dictionary-unmatched forms. Parallel work examines archaism lists and available Romanian lemmatization tools. The intended result is a traceable Cyrillic–Latin corpus with annotations for regionalisms, archaisms, dialectal forms, historical variants, names, and processing errors.
Zitieren
APA
Cojocaru, S., Petic, M., Malahov, L., Caftanatov, O., & Colesnicov, A. (2026). An Integrated Digitization and Validation Framework for Bessarabian Folklore Corpora Printed in Soviet Moldavian Cyrillic Script. Computer Science Journal of Moldova, 34(2), 216-232. https://doi.org/10.56415/csjm.v34.10
Vancouver
Cojocaru S, Petic M, Malahov L, Caftanatov O, Colesnicov A. An Integrated Digitization and Validation Framework for Bessarabian Folklore Corpora Printed in Soviet Moldavian Cyrillic Script. Computer Science Journal of Moldova. 2026;34(2):216-232. doi:10.56415/csjm.v34.10
BibTeX
@article{Cojocaru2026,
author = {Cojocaru, Svetlana and Petic, Mircea and Malahov, Ludmila and Caftanatov, Olesea and Colesnicov, Alexandru},
title = {An Integrated Digitization and Validation Framework for Bessarabian Folklore Corpora Printed in Soviet Moldavian Cyrillic Script},
journal = {Computer Science Journal of Moldova},
year = {2026},
volume = {34},
number = {2},
pages = {216--232},
doi = {10.56415/csjm.v34.10}
}
EUVIMED