Pregled bibliografske jedinice broj: 633586
GPKEX: Genetically Programmed Keyphrase Extraction from Croatian Texts
GPKEX: Genetically Programmed Keyphrase Extraction from Croatian Texts // Procedings of the 4th Biennial International Workshop on Balto-Slavic Natural Language Processing
Sofija: Association for Computational Linguistics (ACL), 2013. str. 43-47 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 633586 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
GPKEX: Genetically Programmed Keyphrase Extraction from Croatian Texts
Autori
Bekavac, Marko ; Šnajder, Jan
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Procedings of the 4th Biennial International Workshop on Balto-Slavic Natural Language Processing
/ - Sofija : Association for Computational Linguistics (ACL), 2013, 43-47
Skup
4th Biennial International Workshop on Balto-Slavic Natural Language Processing
Mjesto i datum
Sofija, Bugarska, 08.08.2013. - 09.08.2013
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Keyphrase extraction; genetic programming; information extraction; Croatian language
Sažetak
We describe GPKEX, a keyphrase extraction method based on genetic programming. We represent keyphrase scoring measures as syntax trees and evolve them to produce rankings for keyphrase candidates extracted from text. We apply and evaluate GPKEX on Croatian newspaper articles. We show that GPKEX can evolve simple and interpretable keyphrase scoring measures that perform comparably to more complex machine learning methods previously developed for Croatian.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Projekti:
036-1300646-1986 - Otkrivanje znanja u tekstnim podacima (Dalbelo-Bašić, Bojana, MZO ) ( CroRIS)
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb
Profili:
Jan Šnajder
(autor)
