Pregled bibliografske jedinice broj: 895048
A machine translation model inspired by code generation
A machine translation model inspired by code generation // Proceedings of 28th Central European Conference on Information and Intelligent Systems (CECIIS 2017) / Strahonja, Vjeran ; Kirinić, Valentina (ur.).
Varaždin: Fakultet organizacije i informatike Sveučilišta u Zagrebu, 2017. str. 187-192 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 895048 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
A machine translation model inspired by code generation
Autori
Radošević, Danijel ; Magdalenić, Ivan ; Andročec, Darko ; Bernik, Andrija ; Kaniški, Matija
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of 28th Central European Conference on Information and Intelligent Systems (CECIIS 2017)
/ Strahonja, Vjeran ; Kirinić, Valentina - Varaždin : Fakultet organizacije i informatike Sveučilišta u Zagrebu, 2017, 187-192
Skup
28th Central European Conference on Information and Intelligent Systems (CECIIS 2017)
Mjesto i datum
Varaždin, Hrvatska, 27.09.2017. - 29.09.2017
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
machine translation, phrase based translation, BLEU
Sažetak
In this paper we present our machine translation model that is based on bilingual linguistic phrases and their lexical attributes. Developed model partly arises from our previous work in the field of Generative Programming, and the working prototype was made for Croatian-French and French-Croatian translation. The model is aimed for the general language domain, but it is so far mostly trained for some limited domains like cooking recipes, weather forecast and user manuals for different devices. The proposed model was evaluated according to the matched phrases and by using the BLEU machine translation evaluation method.
Izvorni jezik
Engleski
Znanstvena područja
Informacijske i komunikacijske znanosti
POVEZANOST RADA
Ustanove:
Fakultet organizacije i informatike, Varaždin
Profili:
Darko Andročec
(autor)
Danijel Radošević
(autor)
Matija Kaniški
(autor)
Ivan Magdalenić
(autor)
Andrija Bernik
(autor)
Citiraj ovu publikaciju:
Časopis indeksira:
- Web of Science Core Collection (WoSCC)
- Conference Proceedings Citation Index - Science (CPCI-S)