20.500.12556/DKUM-20567 SEGMENTACIJA BESEDIL DIPLOMSKIH NALOG IZ DIGITALNE KNJIŽNICE UNIVERZE V MARIBORU TEXT SEGMENTATION OF DIPLOMA WORKS FROM DIGITAL LIBRARY OF THE UNIVERSITY OF MARIBOR Diplomsko delo zajema predstavitev načrtovanja in implementacije programske rešitve za segmentiranje diplomskih del iz Digitalne knjižnice Univerze v Mariboru (DKUM). V delu smo najprej opisali področje procesiranja naravnega jezika in ujemanja vzorcev. Zatem smo opisali programsko rešitev. Predstavili smo postopek pridobitve čistega teksta iz dokumentov PDF, nato analizo zgradbe diplomskih nalog in njihovo segmentiranje. Podali smo tudi opis razvojnega okolja ter opisali težave in omejitve, na katere smo naleteli med razvojem programske rešitve. V zaključku smo podali nekaj sklepnih misli o rezultatih in možnostih nadaljnjega dela. This work presents the design and implementation details of the software solution for the segmentation of diplomas available from the digital library of the University of Maribor. First, we describe the theoretical background that covers the fields of natural language processing and pattern matching. Afterwards, we move to the practical aspect of our solution where we present the acquisition, structure analysis, and segmentation of diplomas. The description of development environment, problems, and restrictions that we came across during the process of development is also considered part of the practical aspect. In the conclusion we wrote some final thoughts on results and future work. segmentiranje besedila procesiranje naravnega jezika ujemanje vzorcev regularni izrazi text segmentation natural language processing pattern matching regular expressions true true false [M. Žerdin] Slovenski jezik Angleški jezik Diplomsko delo/naloga 2011-09-22 17:28:01 2011-09-23 13:03:48 2022-04-14 08:02:39 2023-12-26 03:21:07 2011 0 Maribor 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.45:004.5(043.2) 15601430 URN:SI:UM:DK:FAHREQ4Y VS_Zerdin_Marcel_2011.pdf VS_Zerdin_Marcel_2011.pdf 1 55DED23294258670BE15830F46703F74 faaa99e4aa223f2379d525b4e9127d3e8ad3fd78c13b32b979ec01c9ba731cd6 a6bdc3d9-7c05-11eb-bb7a-00155d0001ca 20.500.12556/dkum/db284267-8cf3-4d48-93f5-596c7e0af44a https://dk.um.si/Dokument.php?lang=slv&id=25568 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0