srp Analiza strukture kolekcije pravnih dokumenata na osnovu njihove povezanosti preko određenih jezičkih izraza [6], 151 list 3057553 bytes Stojković, Suzana 1966- Stanković, Milena Janković, Dragan Bogdanović, Miloš Ivanović, Mirjana 2020 This document employs a statistical approach in exploring language and extracting linguistic forms there contained, so as to identify the linguistic forms which are most frequently used in legal documents. Thus retrieved data can be used to research information, analyze references and links, trace pathways between correlating legal documents and establish the relevance of legal documents on the grounds of their mutual correlation. The retrieved data can further be utilized in various other manners. The methodology of this research and thus attained information form a good basis and act as input data for numerous further analyses. Biografija autora: list 148;Bibliografija: list. 112-118. Datum odbrane: 01.09.2020. Text mining, Natural language processing, Information extraction info:eu-repo/semantics/bachelorThesis All rights reserved https://phaidrani.ni.ac.rs/o:1674 cobiss:21834761 thesis:7841 Petrović, Đorđe, 1970-