Please use this identifier to cite or link to this item: https://research.matf.bg.ac.rs/handle/123456789/1654
Title: Nov metod ekstrakcije informacija baziran na transduktorima
Authors: Pajić, Vesna
Pajić, Miloš
Vujičić Stanković, Staša 
Affiliations: Informatics and Computer Science 
Keywords: Information extraction;natural language processing;data structuring
Issue Date: 2012
Publisher: Beograd : Fakultet organizacionih nauka
Journal: Info M
Abstract: 
U radu je dat osvrt na oblast ekstrakcije informacije, čije su metode i tehnike nezaobilazne u pretrazi i upravljanju
informacijama. Ova oblast u sebi sadrži tehnike drugih oblasti matematike i računarstva, kao što su obrada prirodnih jezika,
teorija formalnih jezika, verovatnoća i statistika. Uzimajući u obzir sve specifičnosti zahteva za informacijom i tekstualnih
resursa iz kojih se izdvajanje vrši, razvijen je i u radu prikazan nov metod za ekstrakciju informacija nazvan Dvofazni metod
baziran na transduktorima. Predstavljena je arhitektura sistema koji implementira ovaj metod kao i primer konkretne primene.
Poseban značaj ovaj metod ima u situacijama kada ne postoje već pripremljeni tekstualni korpusi, neophodni za primenu
postojećih metoda, posebno onih baziranih na verovatnoći i statistici.

An overview of the information extraction is given, whose methods and techniques are indispensable in the information search and information management. Information extraction uses and combines techniques and methods from mathematics and computer science, such as natural language processing, formal language theory, probability and statistics. Taking
into account all specifics of requests for information and textual resources from which it is extracted, we developed and present
a new method for the information extraction called a two-stage method based on the transducers. An architecture of a system
that implements this method is presented, along with an example of application. This method has the special significance in
situations in which there is a lack of already annotated text corpora, that are necessary for the application of existing methods, especially those based on probability and statistics.
URI: https://research.matf.bg.ac.rs/handle/123456789/1654
ISSN: 1451–4397
Appears in Collections:Research outputs

Show full item record

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.