| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:RAZREŠEVANJE VEČPOMENSKOSTI IN ODKRIVANJE USTREZNIH PREDLOG V SISTEMU ZA PRIKLIC INFORMACIJ V NARAVNEM JEZIKU
Authors:ID Bregant, Albin (Author)
ID Ojsteršek, Milan (Mentor) More about this mentor... New window
Files:.pdf MAG_Bregant_Albin_2011.pdf (1,49 MB)
MD5: 8CEE4A1B1B5483CF919A1395103A6756
PID: 20.500.12556/dkum/1974d8a0-9cc2-4b88-a86a-801524000533
 
Language:Slovenian
Work type:Master's thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V magistrskem delu predstavljamo svoj način predstavitve znanja v strukturirani, formalni obliki in način poizvedovanja po tako predstavljenem znanju. Pri obdelavi naravnega jezika smo se osredotočili na neslovnične pristope, brez uporabe slovničnih analiz in korpusov. Predstavljene pristope smo uporabili na sistemu za priklic informacij v naravnem jeziku, kjer uporabniki podajo iskalno zahtevo v naravnem jeziku. Eden izmed osrednjih problemov naravnega jezika je njegova dvoumnost. Če želimo pripraviti ustrezni odgovor, moramo razumeti vprašanje oz. določiti njegov pomen. V pričujočem delu predstavljamo algoritem za razreševanje večpomenskosti in odkrivanje ustreznih predlog, ki nam iz naše baze znanja poišče najustreznejši odgovor.
Keywords:razločevanje entitet, razpoznavanje entitet, razreševanje večpomenskosti, obdelava naravnega jezika, sistem za priklic informacij, predstavitev znanja
Place of publishing:Maribor
Publisher:[A. Bregant]
Year of publishing:2011
PID:20.500.12556/DKUM-18670 New window
UDC:004.5:004.77(043)
COBISS.SI-ID:15192598 New window
NUK URN:URN:SI:UM:DK:IJKAWIWX
Publication date in DKUM:01.07.2011
Views:3331
Downloads:201
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:WORD SENSE DISAMBIGUATION AND TEMPLATE SEARCH IN INFORMATION RETRIEVAL SYSTEMS USING NATURAL LANGUAGE
Abstract:In this master thesis, we propose a knowledge presentation in a structured, formalized form and an approach to query the data presented in such a way. We focused on non-grammatical approaches, without using grammar analysis or corpuses. The proposed approaches were used with an information retrieval system, where users submit their query in natural language. A major problem with natural languages is their ambiguity. If we want to return a suitable answer, we have to understand the question and define its meaning. In this thesis, we propose an algorithm for word sense disambiguation and template search, which retrieves the most suitable answer from our knowledge database.
Keywords:entity resolution, entity recognition, word sense disambiguation, natural language processing, information retrieval system, knowledge representation


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