Naslov
Named Entity Recognition in Croatian Tweets

Autori
Baksa, Krešimir ; Dolović, Dino ; Glavaš, Goran ; Šnajder, Jan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the Ninth Language Technologies Conference, Information Society (IS-JT 2014) / - Ljubljana, 2014, 85-89

Skup
Ninth Language Technologies Conference, Information Society (IS-JT 2014)

Mjesto i datum
Ljubljana, Slovenija, 09.10.2014. - 10.10.2014

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Named entity recognition; information extraction; twitter data; Croatian language

Sažetak
Existing named entity extraction tools, typically designed for formal texts written in standard language (e.g., news stories, essays, or legal texts), do not perform well on user-generated content (e.g., tweets). In this paper we present a supervised approach for named entity recognition and classification for Croatian tweets. Comparison of three different sequence labeling models (HMM, CRF, and SVM) revealed that CRF is the best model for the task, achieving a micro-averaged F1-score of over 87%. We also demonstrate that the state-of-the-art NER model designed for Croatian standard language texts performs much worse than our Twitter-specific NER models.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA