--- title: "Towards a Bulgarian Historical Newspaper Corpus –" description: "Before any linguistic processing, a corpus of Bulgarian newspapers from 1878 to the mid-20th century needs the text on each… 4 references." authors: ["Nikolay Paev", "Stefan Marinov", "Ivan Kratchanov", "Petya Osenova", "Kiril Simov"] year: 2026 venue: "Proceedings of the First Workshop on Creating Interoperable Corpora of Historical Newspapers" source: "https://aclanthology.org/2026.pressmint-1.10/" doi: "10.63317/336sd7ixv3fw" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/paev-2026-bulgarian-historical-newspaper-corpus-construction/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/paev-2026-bulgarian-historical-newspaper-corpus-construction/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/53/) / Towards a Bulgarian Historical Newspaper Corpus – Construction of Reading Order over the Text in Searchable PDFs # Towards a Bulgarian Historical Newspaper Corpus – Construction of Reading Order over the Text in Searchable PDFs **Authors:** [Nikolay Paev](https://md.research.elamur.ai/free/en/authors/nikolay-paev/), [Stefan Marinov](https://md.research.elamur.ai/free/en/authors/stefan-marinov/), Ivan Kratchanov, [Petya Osenova](https://md.research.elamur.ai/free/en/authors/petya-osenova/) and [Kiril Simov](https://md.research.elamur.ai/free/en/authors/kiril-simov/) · **Year:** 2026 · **Venue:** [Proceedings of the First Workshop on Creating Interoperable Corpora of Historical Newspapers](https://md.research.elamur.ai/free/en/venues/pressmint/) ([Workshop on Creating Interoperable Corpora of Historical Newspapers 2026](https://md.research.elamur.ai/free/en/venues/pressmint/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.pressmint-1.10/) · [PDF](https://aclanthology.org/2026.pressmint-1.10.pdf) · [DOI 10.63317/336sd7ixv3fw](https://doi.org/10.63317/336sd7ixv3fw) · [OpenAlex](https://openalex.org/W7166541280) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary Before any linguistic processing, a corpus of Bulgarian newspapers from 1878 to the mid-20th century needs the text on each page placed in its intended reading sequence. The sources are searchable PDFs from the "Ivan Vazov" National Library in Plovdiv. They were OCR-ed with ABBYY FineReader, which the team further trained on historical Cyrillic letters and non-standard fonts. Page layouts change constantly, so the text blocks in these PDFs have no dependable order, and articles end up interleaved. The authors built a page-processing algorithm that organizes extracted blocks into subpages and columns and then orders them. They compared it against plain off-the-shelf library extraction. For evaluation, they created a manually corrected gold dataset and scored outputs with a Levenshtein-type edit distance. The same metric guided a grid search over the algorithm's parameters, cutting the required edits by about 10%. A small editing tool supports the remaining manual fixes. The approach does not depend on the language and is a precondition for reliable article extraction at scale. ## Key points - The library's archival masters are 24-bit colour scans at 300 ppi. The public PDFs are lower-quality files produced by ABBYY FineReader, which was given targeted training snippets for obsolete letters such as yat and big nosovka. - Over the gold dataset, the edit distance fell from 1925 with intuitive initial parameters to 1702 after a grid search of more than 20,000 parameter combinations. - The tuned parameters include x_tolerance, partial_gap_threshold, min_column_page_ratio and min_column_width. Tuning per newspaper subset gave gains of up to 60% over the globally optimal settings. - The output is XML structured as pages → subpages → columns → blocks → text. Manual post-editing relies on three operations: classifying blocks as normal, meta or noise; adjusting block coordinates; and swapping block order. - The full collection exceeds 150,000 pages across more than 300 titles. Planned work includes fine-tuning an encoder transformer on subwords with 2D positions, plus article segmentation and spelling normalization. The work is supported by CLaDA-BG (CLARIN/DARIAH). *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [Bulgarian Academy of Sciences](https://md.research.elamur.ai/free/en/government/bulgarian-academy-of-sciences/) — Government body, Sofia, Bulgaria · 7 works · 554 citations - [Institute of Information and Communication Technologies](https://md.research.elamur.ai/free/en/labs/institute-of-information-and-communication-technologies/) — Research institute, Sofia, Bulgaria · 3 works · 10 citations Also on the byline: [Ivan Vazov National Library](https://ror.org/04pms6p91). 📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [📚 Literature and Literary Theory](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/literature-and-literary-theory/) · 541 works ## Cite Cite as: Nikolay Paev, Stefan Marinov, Ivan Kratchanov, Petya Osenova and Kiril Simov. 2026. Towards a Bulgarian Historical Newspaper Corpus – Construction of Reading Order over the Text in Searchable PDFs. Proceedings of the First Workshop on Creating Interoperable Corpora of Historical Newspapers. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{paev2026bulgarian, title = {{Towards a Bulgarian Historical Newspaper Corpus – Construction of Reading Order over the Text in Searchable PDFs}}, author = {Nikolay Paev, Stefan Marinov, Ivan Kratchanov, Petya Osenova and Kiril Simov}, booktitle = {Proceedings of the First Workshop on Creating Interoperable Corpora of Historical Newspapers}, year = {2026}, doi = {10.63317/336sd7ixv3fw}, url = {https://doi.org/10.63317/336sd7ixv3fw} } ``` - [← previous Toward Robust In-Context Learning: Leveraging Out-of-distribution Proxies for Target Inaccessible Demonstration Retrieval](https://md.research.elamur.ai/free/en/papers/xu-2026-robust-context-learning-leveraging-out/) - [next → Towards a Gold Standard for Adjectival Hypernymy: Enriching the Open English WordNet with a Hybrid Approach](https://md.research.elamur.ai/free/en/papers/augello-2026-gold-standard-adjectival-hypernymy-enriching/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/53/) ## References 4 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Jonathan Bourne. 2025. [Reading the unreadable: creating a dataset of 19th century english newspapers using image-to-text language models](https://md.research.elamur.ai/free/en/papers/bourne-2025-reading-unreadable-creating-dataset-19th/). Digital Scholarship in the Humanities, page fqaf151. 2. Xiaowen Ding and Weiqun Huang. 2014. Pdf converter production of historical newspaper digitization: The picture experience of china’s dachenglaojiu database. In Proceedings of the International Newspaper Conference, IFLA. International Federation of Library Associations and Institutions (IFLA). [find](https://scholar.google.com/scholar?q=Xiaowen+Ding+and+Weiqun+Huang%2E+2014%2E+Pdf+converter+production+of+historical+newspaper+digitization%3A+The+picture+experience+of+china%E2%80%99s+dachenglaojiu+database%2E+In+Proceedings+of+the+International+Newspa) 3. Nicolas Gutehrlé and Iana Atanassova. 2021. Logical layout analysis applied to historical newspapers. In Proceedings of the Workshop on Natural Language Processing for Digital Humanities, pages 85–94, NIT Silchar, India. NLP Association of India (NLPAI). [find](https://scholar.google.com/scholar?q=Nicolas+Gutehrl%C3%A9+and+Iana+Atanassova%2E+2021%2E+Logical+layout+analysis+applied+to+historical+newspapers%2E+In+Proceedings+of+the+Workshop+on+Natural+Language+Processing+for+Digital+Humanities%2C+pages+85%E2%80%9394%2C) 4. Loryn Isaacs, Santiago Chambó, and Pilar León-Araúz. 2024. Humanitarian corpora for English, [find](https://scholar.google.com/scholar?q=Loryn+Isaacs%2C+Santiago+Chamb%C3%B3%2C+and+Pilar+Le%C3%B3n%2DAra%C3%BAz%2E+2024%2E+Humanitarian+corpora+for+English%2C) *Updated 1 November 2026*