Your browser does not allow JavaScript!
JavaScript is necessary for the proper functioning of this website. Please enable JavaScript or use a modern browser.
Repository of the University of Ljubljana
Open Science Slovenia
Open Science
DiKUL
slv
|
eng
Search
Advanced
New in RUL
About RUL
In numbers
Help
Sign in
Details
Razvrščanje sopomenskih kandidatov z uporabo ChatGPT : raziskovalni podatki, obravnavani v doktorskem delu
ID
Gapsa, Magdalena
(
Author
)
DOCX - Data description,
Download
(2,61 MB)
MD5: E7C686724AA7234064651F18AAA09168
Description: PREBERI ME - README
TXT - Data description,
Download
(3,47 KB)
MD5: A56FA0BF8EE05D59693DEC29FBE9E802
Description: Log file
XLSX - Research data,
Download
(28,50 KB)
MD5: F6F5EBC5E0C64B645F1F563D4B1542D9
Description: Input data XLSX
This document has even more files. Complete list of files is available
below
.
Image galllery
Abstract
Podatkovna zbirka prikazuje vhodne in izhodne podatke za poskus uporabe sistema ChatGPT za čiščenje strojno pridobljenih sopomenskih kandidatov in njihovo umeščanje pod ustrezne besedne pomene. Podatki so nastali z uporabo baz Slovarja sopomenk sodobne slovenščine v njegovi prvi (1.0) in drugi (2.0) različici. Kot vhodni podatki so bili iz SSSS 1.0 izluščeni strojno pridobljeni sopomenski kandidati, iz SSSS 2.0 pa podatki o pomenski členitvi posameznih iztočnic. Izhodni podatki prikazujejo rezultate razvrstitve sopomenskih kandidatov, ki jo je opravil API model GPT-4 na podlagi poziva, ki je zabeležen v dnevniški datoteki. Postopek analize podatkov je podrobneje opisan v članku »Kako dober je ChatGPT pri umeščanju sopomenk pod besedne pomene« (Gapsa, Arhar Holdt in Kosem, 2024). Timotej Petrič, študent Fakultete za računalništvo in informatiko Univerze v Ljubljani, je med pripravo raziskovalnih podatkov pomagal pri tehničnih vidikih postopka. Pri pripravi raziskovalnih podatkov je sodeloval Timotej Petrič, študent FRI UL, ki je pomagal pri tehnični izvedbi postopka.
Language:
Slovenian
Keywords:
digitalno slovaropisje
,
ChatGPT
,
sopomenke
,
besedni pomen
,
slovenščina
,
Slovar sopomenk sodobne slovenščine
,
raziskovalni podatki
Typology:
2.20 - Complete scientific database of research data
Time coverage:
Podatki ustvarjeni in analizirani v letu 2024.
Organization:
FF - Faculty of Arts
Year:
2026
PID:
20.500.12556/RUL-181444
Publication date in RUL:
09.04.2026
Views:
18
Downloads:
3
Metadata:
Cite this work
Plain text
BibTeX
EndNote XML
EndNote/Refer
RIS
ABNT
ACM Ref
AMA
APA
Chicago 17th Author-Date
Harvard
IEEE
ISO 690
MLA
Vancouver
:
Copy citation
Share:
Licences
License:
CC BY 4.0, Creative Commons Attribution 4.0 International
Link:
http://creativecommons.org/licenses/by/4.0/
Description:
This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.
Secondary language
Language:
English
Title:
Sorting synonym candidates using ChatGPT : research data underlying the doctoral dissertation
Abstract:
The dataset contains the input and output data for an experiment using the ChatGPT system to clean automatically obtained synonym candidates and assign them to appropriate word senses. The data was compiled using the first (1.0) and second (2.0) versions of the Thesaurus of Modern Slovene (SSSS). Input data include automatically obtained synonym candidates from SSSS 1.0 and word senses of individual headwords from SSSS 2.0. The output data presents the result of the classification of synonym candidates performed by the GPT-4 API model based on the prompt recorded in the log file. The data analysis process is described in detail in the paper "Kako dober je ChatGPT pri umeščanju sopomenk pod besedne pomene " (Gapsa, Arhar Holdt, and Kosem, 2024). Timotej Petrič, a student at the Faculty of Computer and Information Science at the University of Ljubljana, assisted with the technical aspects of the process during the preparation of the research data.
Keywords:
digital lexicography
,
ChatGPT
,
synonyms
,
word senses
,
Slovene language
,
Thesaurus of Modern Slovene
,
research data
Projects
Funder:
ARIS - Slovenian Research and Innovation Agency
Project number:
P6-0411
Name:
Jezikovni viri in tehnologije za slovenski jezik
Similar documents
Similar works from RUL:
Similar works from other Slovenian collections:
Files
Loading...
Back