Pregled bibliografske jedinice broj: 737163
Predicting Croatian Phrase Sentiment Using a Deep Matrix-Vector Model
Predicting Croatian Phrase Sentiment Using a Deep Matrix-Vector Model // Proceedings of the Ninth Language Technologies Conference, Information Society (IS-JT 2014)
Ljubljana, 2014. str. 95-98 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 737163 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Predicting Croatian Phrase Sentiment Using a Deep Matrix-Vector Model
Autori
Biđin, Siniša ; Šnajder, Jan ; Glavaš, Goran
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, 95-98
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
Sentiment analysis; phrase-level sentiment; deep learning; Croatian language
Sažetak
Many sentiment analysis tasks rely on the existence of a sentiment lexicon. Such lexicons, however, typically contain single words annotated with prior sentiment. Problems arise when trying to model the sentiment of multiword phrases such as “very good” or “not bad”. In this paper, we use a recently proposed deep neural network model to classify the sentiment of phrases in Croatian. The experimental results suggest that reasonable classification of phrase-level sentiment for Croatian is achievable with such a model, reaching a performance comparable to that of an analogous model for English.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb
