Prospective automated hierarchical classification of digitized documents
Review of the National Center for Digitization, Tome 29 (2016) no. 1.

Voir la notice de l'article provenant de la source eLibrary of Mathematical Institute of the Serbian Academy of Sciences and Arts

The paper presents a proposal of a method for hierarchical classification of digitized documents of NCD digital library. The classification model implements Structured Support Vector Machine method (SSVM) which has shown excellent performance on Ebart corpus of documents in Serbian language. We describe the developed model and its results on Ebart dataset, suggest two types of hierarchies of classes of the NCD library regarding its content and define a protocol for the application of the method to digitized documents.
@article{NCD_2016_29_1_a5,
     author = {Jovana Kova\v{c}evi\'c and Jelena Graovac},
     title = {Prospective automated hierarchical classification of digitized documents},
     journal = {Review of the National Center for Digitization},
     pages = {42 - 51},
     publisher = {mathdoc},
     volume = {29},
     number = {1},
     year = {2016},
     url = {http://geodesic.mathdoc.fr/item/NCD_2016_29_1_a5/}
}
TY  - JOUR
AU  - Jovana Kovačević
AU  - Jelena Graovac
TI  - Prospective automated hierarchical classification of digitized documents
JO  - Review of the National Center for Digitization
PY  - 2016
SP  - 42 
EP  -  51
VL  - 29
IS  - 1
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/NCD_2016_29_1_a5/
ID  - NCD_2016_29_1_a5
ER  - 
%0 Journal Article
%A Jovana Kovačević
%A Jelena Graovac
%T Prospective automated hierarchical classification of digitized documents
%J Review of the National Center for Digitization
%D 2016
%P 42 - 51
%V 29
%N 1
%I mathdoc
%U http://geodesic.mathdoc.fr/item/NCD_2016_29_1_a5/
%F NCD_2016_29_1_a5
Jovana Kovačević; Jelena Graovac. Prospective automated hierarchical classification of digitized documents. Review of the National Center for Digitization, Tome 29 (2016) no. 1. http://geodesic.mathdoc.fr/item/NCD_2016_29_1_a5/