Naslov
Can we beat Google Translate?

Autori
Brkic, M. ; Mikulic, B.B. ; Matetic, M.

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

Izvornik
Proceedings of the ITI 2012 34th Conf. on Information Technology Interfaces  / Luzar-Stiffler, Vesna ; Jarec, Iva ; Bekic, Zoran - Zagreb : Sveučilišni računski centar Sveučilišta u Zagrebu (Srce), 2012, 381-386

ISBN
978-953-7138-24-0

Skup
Conf. on Information Technology Interfaces

Mjesto i datum
Cavtat, Hrvatska, 25.06.2012. - 28.06.2012

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
automatic evaluation; BLEU; F-measure; Google Translate; NIST; PER; reference set; SMT (statistical machine translation); TER; translation evaluation; WER

Sažetak
This paper presents a machine translation evaluation study for CroatianEnglish language pair. In-domain and out-of-domain translations from Croatian into English have been obtained from Google Translate, our own statistical machine translation system LegTran, and from a professional translator. These translations have been evaluated by six different automatic metrics. The gains obtained from increasing the number of reference translations have been explored and measured. System level correlation between automatic evaluation metrics is given and the significance of the results is discussed. Bootstrapping, approximate randomization and the sign test have been used for confidence intervals and hypothesis testing.

Izvorni jezik
Engleski

Znanstvena područja
Informacijske i komunikacijske znanosti

POVEZANOST RADA