| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Odkrivanje podobnih vsebin s pomočjo pomenskih podpisov in pomenskega stiskanja
Authors:ID Majninger, Sandi (Author)
ID Ojsteršek, Milan (Mentor) More about this mentor... New window
ID Brezovnik, Janez (Comentor)
Files:.pdf MAG_Majninger_Sandi_2017.pdf (2,45 MB)
MD5: 612E2F7C966BA30A0319A5E0F9A4AEDD
PID: 20.500.12556/dkum/ded3cb50-7e66-4533-8f7d-1c2b465fc3ed
 
Language:Slovenian
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V magistrskem delu smo razvili postopek za odkrivanje podobnih vsebin s pomočjo primerjave pomena odstavkov. V ta namen smo izračunali pomenske podpise posameznih odstavkov in jih primerjali med seboj. Takšen način nam omogoča odkrivanje parafraziranih in prevedenih besedil. Preverjali smo vpliv uporabe pomenskega stiskanja na končno uspešnost postopka. Zanimalo nas je tudi, kako na uspešnost vpliva izbira pomenskega slovarja. Ugotovili smo, da lahko s pomočjo pomenskega stiskanja in uporabe obsežnejših slovarjev zmanjšamo občutljivost na spremembe besedila, tako da odkrijemo več podobnosti.
Keywords:odkrivanje podobnih vsebin, pomenski podpis, pomensko stiskanje, pomenski slovar, plagiat
Place of publishing:Maribor
Publisher:[S. Majninger]
Year of publishing:2017
PID:20.500.12556/DKUM-67281 New window
UDC:004.93'1(043.2)
COBISS.SI-ID:20854294 New window
NUK URN:URN:SI:UM:DK:QXFRPAEU
Publication date in DKUM:30.08.2017
Views:1704
Downloads:178
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
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-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:09.08.2017

Secondary language

Language:English
Title:Detection of similar content using semantic signatures and semantic compression
Abstract:In this thesis, we developed a process for discovering similar contents by comparing the meaning of the paragraphs. For this purpose, we calculated semantic signatures of each paragraph and used them for comparison. That allows us to detect paraphrased and translated texts. We examined the impact of semantic compression on the final performance of the process. We were also interested in how different semantic dictionaries influences the performance. We found out that with the help of a semantic compression and the use of more extensive dictionaries, we can reduce the sensitivity to text changes, so it discovers more similarities.
Keywords:detection of similar content, semantic signature, semantic compression, semantic dictionary, plagiarism


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica