Преглед НЦД 22 (2013), 140–147

Marija Šegan

Mathematical Institute of SASA

Natural Sciences and Technologies, University of Belgrade, Serbia

Nikola Petrović

Morena inženjering Niš, Serbia

ARCHIVE OF THE MATHEMATICAL INSTITUTE OF

THE SERBIAN ACADEMY OF SCIENCES AND ARTS:

DIGITIZATION OF THE REPORTS FROM THE SESSIONS OF

THE SCIENTIFIC COUNCIL (1948 – 1964)

Abstract: The Archive of the Mathematical Institute of Serbian Academy of Sciences and Arts (MI SASA) exists from the date of the establishment of the Institute as its integral part, and includes more than a dozen of handwritten volumes (i.e. reports, diaries, and journals), that testifies to its financial, administrative, technical, cultural, scientific and other activities. Although the archive is formally open to the public, , access to information is in practice limited; so there is an initiative to use digitization, preserve the archival material, provide a presentation and open access to the users. Using the example of digitization of the oldest preserved report manuscript from the sessions of the Scientific Council of MI SASA (1948 – 1964), this paper deals with following questions: 1) the standards of digitization of the old manuscripts in the absence of a unified national strategy for digitization of the cultural heritage, and 2) the named entity recognition – automatic extraction and linking of a person, other named entities and keywords from the digitized manuscripts in order to facilitate its effective search. The results of this paper are presented in HTML presentation.

Keywords: MI SANU Archive, cultural heritage, digital preservation, OCR/ICR, NLP, NER