Repository of colleges and higher education institutions

Show document
A+ | A- | Help | SLO | ENG

Title:S poizvedovanjem obogateno generiranje teksta za delo z dokumentacijo s področja naravovarstva : magistrska naloga
Authors:ID Gatej, Gregor (Author)
ID Boškoski, Pavle (Mentor) More about this mentor... New window
Files:.pdf MAG_2025_Gregor_Gatej.pdf (5,49 MB)
MD5: 9FF8F3847B88F7C83B405F19AB05CFF0
 
Language:Slovenian
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FIŠ - Faculty of Information Studies in Novo mesto
Abstract:Zavod Republike Slovenije za varstvo narave (ZRSVN) se srečuje s težavo učinkovitega pridobivanja informacij iz obsežne zbirke dokumentov o spremljanju stanja živalskih in rastlinskih vrst, kar gre pripisati nestrukturirani naravi dokumentov. Namen magistrske naloge je razviti praktično rešitev, ki bo omogočila hitrejši in natančnejši dostop do informacij iz navedenih dokumentov. Naloga obsega pripravo in strukturiranje besedilnega korpusa, razvoj prototipa sistema za s poizvedovanjem obogateno generiranje teksta (ang. Retrieval Augmented Generation ali s kratico RAG) ter izdelavo spletne aplikacije za evaluacijo avtomatsko generiranih vprašanj in odgovorov.
Keywords:s poizvedovanjem obogateno generiranje teksta, naravovarstvo, iskanje, nestrukturirani podatki, avtomatska evaluacija, procesiranje naravnega jezika, veliki jezikovni modeli
Place of publishing:Novo mesto
Place of performance:Novo mesto
Publisher:G. Gatej
Year of publishing:2025
Year of performance:2025
Number of pages:XV, 76 str.
PID:20.500.12556/ReVIS-12440 New window
COBISS.SI-ID:253438979 New window
UDC:004.89(043.2)
Note:Na ov.: Magistrska naloga : študijskega programa druge stopnje;
Publication date in ReVIS:17.10.2025
Views:141
Downloads:3
Metadata:XML DC-XML DC-RDF
:
Copy citation
  
Share:Bookmark and Share


Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-SA 4.0, Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International
Link:http://creativecommons.org/licenses/by-nc-sa/4.0/
Description:A Creative Commons license that bans commercial use and requires the user to release any modified works under this license.

Secondary language

Language:English
Abstract:The Institute of the Republic of Slovenia for Nature Conservation (IRSNC) faces the challenge of efficiently retrieving information from an extensive collection of documents monitoring the status of animal and plant species, which is attributed to the unstructured nature of the documents. The purpose of this master’s thesis is to develop a practical solution that will enable faster and more accurate access to information from these documents. The thesis encompasses the preparation and structuring of a textual corpus, the development of a prototype system for Retrieval Augmented Generation (RAG), and the creation of a web application for the evaluation of automatically generated question and answer pairs.
Keywords:retrieval augmented generation, nature conservation, search, unstructured data, automatic evaluation, natural language processing, large language models


Back