@inproceedings{paev-etal-2026-towards,
    title = "Towards a {B}ulgarian Historical Newspaper Corpus {--} Construction of Reading Order over the Text in Searchable {PDF}s",
    author = "Paev, Nikolay  and
      Marinov, Stefan  and
      Kratchanov, Ivan  and
      Osenova, Petya  and
      Simov, Kiril",
    editor = "Ogrodniczuk, Maciej  and
      Osenova, Petya  and
      Wissik, Tanja",
    booktitle = "Proceedings of the First Workshop on Creating Interoperable Corpora of Historical Newspapers",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/paragraph-normalization/2026.pressmint-1.10/",
    doi = "10.63317/336sd7ixv3fw",
    pages = "56--64",
    abstract = "The determine the reading order of the text extracted from a searchable PDF produced by an OCR software from an old newspaper is the first task in the process of preparation of corpora of old newspapers. In the paper we present an algorithm for generation of reading order of black selected from the corresponding PDF. Also we performed a tuning of the parameters of the algorithm. The optimization provides 10 {\%} improvement."
}