Naslov
Recognition of Linguistic Features by Hidden Markov Model(HMM)

Autori
Tepeš, Božidar ; Szirovicza, Lajos ; Sujoldžić, Anita ; Primorac, Martina

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

Izvornik
ITI'97 Proceedings of the 19th International Conference on Information / Kalpić, D. ; Dobrić Hljuz, V. - : Sveučilišni računski centar Sveučilišta u Zagrebu (Srce), 1997, 289-295

Skup
19th International Conference on Information Tehnology Interface

Mjesto i datum
Pula, Hrvatska, 17.06.1997. - 20.06.1997

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Hidden Markov Model; HMM; stohastic tagging; language processing; anthropology

Sažetak
Encouraged by recent results in creating automatic taggers for different European languages, Croatian language, an attempt has been made to use HMM for solving a problem of socio-cultural linguistic microdifferentiation of reproductively isolated small populations in the area of Eastern Adriatic. The intention was to create two distinguished HMM, one capable of recognising the "čakavian" dialect, and the other one for the recognition of the "štokavian" dialect. Recognition of the dialects is based on their differential phonetic characteristics. The paper presents the results achieved in the framework of the HMM for tagging of Croatian language texts, past development of this method for dialects ("čakavian" and "štokavian"), characteristics of dialects, description of corpora available at the moment, short introduction of the HMM as a potential mathematical background for future research and results.

Izvorni jezik
Engleski

Znanstvena područja
Informacijske i komunikacijske znanosti, Etnologija i antropologija

POVEZANOST RADA