@inproceedings{koeva-stoyanova-2026-recent,
    title = "Recent Developments of the {B}ulgarian National Corpus",
    author = "Koeva, Svetla Peneva  and
      Stoyanova, Ivelina",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/backfill-openreview/2026.cmlc-1.10/",
    doi = "10.63317/3m95ohtw7mjs",
    pages = "71--75",
    abstract = "We present recent developments in the Bulgarian National Corpus, including data collection from various sources, cleaning of diverse datasets, enrichment with multimodal data, and extensive metadata, which resulted in the development of IfGPT, a large BulNC-based dataset. Typical methods for distributing the BulNC-based dataset are briefly described, with emphasis on effective searching within the metadata stored in a graph database."
}