Pregled bibliografske jedinice broj: 686583
CroNER: Recognizing Named Entities in Croatian Using Conditional Random Fields
CroNER: Recognizing Named Entities in Croatian Using Conditional Random Fields // Informatica (Ljubljana), 37 (2013), 165-172 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 686583 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
CroNER: Recognizing Named Entities in Croatian Using Conditional Random Fields
Autori
Karan, Mladen ; Glavaš, Goran ; Šarić, Frane ; Šnajder, Jan ; Šilić, Artur ; Dalbelo Bašić, Bojana
Izvornik
Informatica (Ljubljana) (0350-5596) 37
(2013);
165-172
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
named entity recognition ; conditional random fields ; natural language processing ; information extraction ; Croatian language
Sažetak
In this paper we present CroNER, a named entity recognition and classification system for Croatian lan-guage based on supervised sequence labeling with conditional random fields (CRF). We use a rich set of lexical and gazetteer-based features and different methods for enforcing document-level label consistency. Extensive evaluation shows that our method achieves state-of-the-art results (MUC F1 90.73%, Exact F1 87.42%) when compared to existing NERC systems for Croatian and other Slavic languages.
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:
Bojana Dalbelo Bašić
(autor)
Goran Glavaš
(autor)
Artur Šilić
(autor)
Frane Šarić
(autor)
Jan Šnajder
(autor)
Mladen Karan
(autor)
Citiraj ovu publikaciju:
Časopis indeksira:
- Web of Science Core Collection (WoSCC)
- Emerging Sources Citation Index (ESCI)
- Scopus