Processing of Scanned Mathematical PDF Documents in the Semantic Formula Search Service

Main Article Content

Konstantin Sergeevich Nikolaev

Abstract

The article addresses the problem of extracting semantic relations between mathematical formulas and concepts from unstructured PDF documents, including scanned ones. A complete processing pipeline is proposed that combines optical character recognition, paragraph structure recovery, formula and variable extraction, and their linking to concepts using syntactic patterns of the Russian language. Formal models are developed for two types of relations: "variable-concept" and "variable-main formula". Experimental evaluation on a collection of 150 mathematical articles shows a significant improvement in linking accuracy, with an increase of 18 percentage points in F-measure compared to the previous version. Architectural improvements of the web service prototype are described, providing asynchronous processing and scalability.

Article Details

How to Cite
Nikolaev, K. S. “Processing of Scanned Mathematical PDF Documents in the Semantic Formula Search Service”. Russian Digital Libraries Journal, vol. 29, no. 6, Oct. 2026, pp. 2555-72, doi:10.26907/1562-5419-2026-29-6-2555-2572.

References

1. Smith R. An overview of the tesseract OCR engine // Proc. Int. Conf. Doc. Anal. Recognition, ICDAR. 2007. Vol. 2. P. 629–633. https://doi.org/10.1109/ICDAR.2007.4376991
2. Constantin A., Pettifer S., Voronkov A. PDFX: Fully-automated PDF-to-XML conversion of scientific literature // DocEng 2013 – Proc. 2013 ACM Symp. Doc. Eng. 2013. P. 177–180. https://doi.org/10.1145/2494266.2494271
3. Ciancarini P., Iorio A. Di, Nuzzolese A. G., Peroni S., Vitali F. Semantic annotation of scholarly documents and citations // Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics). 2013. Vol. 8249 LNAI. P. 336–347. https://doi.org/10.1007/978-3-319-03524-6_29
4. Amethiya Y., Bajwa G. Automatic Table Detection and Tabular Data Extraction from Scanned Documents // Smart Innovation, Systems and Technologies. 2025. P. 75–87. https://doi.org/10.1007/978-981-96-0143-1_7
5. Bertin M., Atanassova I. Hybrid Approach for the Semantic Processing of Scientific Papers // Semant. Publ. Chall. Track 11 th Eur. Semant. Web Conf. (ESWC 2014). 2014. https://doi.org/10.1007/978-981-96-0143-1_7
6. Ahmad R., Afzal M. T., Qadir M. A. Information extraction from PDF sources based on rule-based system using integrated formats // Commun. Comput. Inf. Sci. 2016. Vol. 641. P. 293–308. https://doi.org/10.1007/978-3-319-46565-4_23
7. Schubotz M., Greiner-Petter A., Scharpf P., Meuschke N., Cohl H. S., Gipp B. Improving the Representation and Conversion of Mathematical Formulae by Considering their Textual Context // Proc. ACM/IEEE Jt. Conf. Digit. Libr. 2018. P. 233–242. https://doi.org/10.1145/3197026.3197058
8. Mathematical Markup Language (MathML) Version 3.0 2nd Edition. W3C Recommendation, 10 April 2014. URL: https://www.w3.org/TR/MathML3/
9. Greiner-Petter A., Youssef A., Ruas T., Miller B. R., Schubotz M., Aizawa A., Gipp B. Math-word embedding in math search and semantic extraction // Scientometrics. 2020. Vol. 125, No. 3. P. 3017–3046. https://doi.org/10.1007/s11192-020-03502-9
10. Nevzorova O., Kirillovich A., Nevzorov V., Nikolaev K. The semantic context models of mathematical formulas in scientific papers // CEUR Workshop Proc. 2018. Vol. 2277. P. 33–40.
11. Shah A. K., Dey A., Zanibbi R. A Math Formula Extraction and Evaluation Framework for PDF Documents // Lecture Notes in Computer Science. 2021. P. 19–34. https://doi.org/10.1007/978-3-030-86331-9_2
12. Siegel N., Lourie N., Power R., Ammar W. Extracting Scientific Figures with Distantly Supervised Neural Networks // Proc. ACM/IEEE Jt. Conf. Digit. Libr. 2018. P. 223–232. https://doi.org/10.1145/3197026.3197040
13. Semantic Scholar. URL: https://www.semanticscholar.org/
14. Neudecker C., Baierer K., Gerber M., Clausner C., Antonacopoulos A., Pletschacher S. A survey of OCR evaluation tools and metrics // The 6th International Workshop on Historical Document Imaging and Processing. New York, NY, USA: ACM, 2021. P. 13–18. https://doi.org/10.1145/3476887.3476888
15. Jaradeh M. Y., Oelen A., Farfar K. E., Prinz M., D'Souza J., Kismihók G., Stocker M., Auer S. Open research knowledge graph: Next generation infrastructure for semantic scholarly knowledge // K-CAP 2019 – Proceedings of the 10th International Conference on Knowledge Capture. New York, NY, USA: ACM, 2019. P. 243–246. https://doi.org/10.1145/3360901.3364435
16. Peroni S., Shotton D. FaBiO and CiTO: Ontologies for describing bibliographic resources and citations // J. Web Semant. 2012. Vol. 17. P. 33–43. https://doi.org/10.1016/j.websem.2012.08.001
17. Nikolaev K.S. Servis semanticheskogo poiska formul po kollekcii matematicheskih PDF-dokumentov // Informacionnye tehnologii i vychisli-tel'nye sistemy. 2025. № 3. S. 34–43. https://doi.org/10.14357/20718632250304
18. Kirillovich A. V., Nevzorova O. A., Lipachev E. K. OntoMathPRO 2.0 Ontology: Updates of Formal Model // Lobachevskii J. Math. 2022. Vol. 43, No. 12. P. 3504–3514. https://doi.org/10.1134/S1995080222150136
19. MSC2020 –Mathematics Subject Classification System. URL: https://msc2020.org/.
20. Celery –Distributed Task Queue. URL: https://docs.celeryq.dev/.
21. Redis – The real-time context engine for AI apps. URL: https://redis.io/.


Most read articles by the same author(s)