| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Uporaba analitike besedil za samodejno gradnjo semantične mreže na osnovi ključnih besed
Authors:ID Majer, Črtomir (Author)
ID Podgorelec, Vili (Mentor) More about this mentor... New window
Files:.pdf MAG_Majer_Crtomir_2017.pdf (6,02 MB)
MD5: 2C24BA6067428F5675366468D68AE092
 
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 se spopadli s problemom samodejne gradnje računalniške baze znanja, z uporabo analitike besedil in tehnik nenadzorovanega strojnega učenja. Definirali in implementirali smo proces, ki je zmožen iz domensko-specifičnega korpusa besedil ustvariti semantično mrežo. Ta vsebuje ključne koncepte in relacije med njimi, ki se pojavljajo znotraj izbranega področja, katerega določimo s ključnimi besedami. Pri tem uporabimo številne metode, kot so procesiranje naravnega jezika, odprto pridobivanje informacij, vektorska predstavitev besed (word2vec), gručenje in druge tehnike odkrivanja znanja. Predstavimo tudi lastne rešitve in izboljšave, ki pripomorejo k uspešnejši gradnji semantične mreže.
Keywords:analitika besedil, semantična mreža, odprto pridobivanje informacij, word2vec, nenadzorovano učenje
Place of publishing:[Maribor
Publisher:Č. Majer
Year of publishing:2017
PID:20.500.12556/DKUM-66528 New window
UDC:004.82:004.65(043.2)
COBISS.SI-ID:20969238 New window
NUK URN:URN:SI:UM:DK:XI2KR2SA
Publication date in DKUM:17.10.2017
Views:1527
Downloads:206
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.

Secondary language

Language:English
Title:Using text analytics to automatically build semantic networks based on keywords
Abstract:In this master's thesis, we tackle the problem of automatic knowledge database construction, using text analytics and unsupervised machine learning techniques. We've defined and implemented a process, capable of building a semantic network from a domain-specific corpus. A network includes key concepts and relationships, occurring within selected domain, that is defined by keywords. To achieve that, we used a number of methods, such as natural language processing, open information extraction, word embedding (word2vec), clustering and other techniques for knowledge discovery. We also introduced our own solutions and improvements that contribute to a successful construction of a semantic network.
Keywords:text analytics, semantic network, open information extraction, word2vec, unsupervised learning


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