Evaluation of the Statistical Machine Translation Service for Croatian-English

Much thought has been given in an endeavour to formalize the translation process. As a result, various approaches to MT (machine translation) were taken. With the exception of statistical translation, all approaches require cooperation between language and computer science experts. Most of the model...

Full description

Permalink: http://skupni.nsk.hr/Record/ffzg.KOHA-OAI-FFZG:316467/Details
Matična publikacija: 2nd international conference The future of information sciences (INFuture 2009) : Digital resources and knowledge sharing : proceedings
Zagreb : Department of Information Sciences, Faculty of Humanities and Social Sciences, University of Zagreb, 2009
Glavni autori: Brkić, Marija (-), Vičić, Tomislav (Author), Seljan, Sanja
Vrsta građe: Članak
Jezik: eng
LEADER 02509naa a2200265uu 4500
008 131111s2009 xx 1 eng|d
035 |a (CROSBI)433160 
040 |a HR-ZaFF  |b hrv  |c HR-ZaFF  |e ppiak 
100 1 |a Brkić, Marija 
245 1 0 |a Evaluation of the Statistical Machine Translation Service for Croatian-English /  |c Brkić, Marija ; Vičić, Tomislav ; Seljan, Sanja. 
246 3 |i Naslov na engleskom:  |a Evaluation of the Statistical Machine Translation Service for Croatian-English 
300 |a 319-332  |f str. 
520 |a Much thought has been given in an endeavour to formalize the translation process. As a result, various approaches to MT (machine translation) were taken. With the exception of statistical translation, all approaches require cooperation between language and computer science experts. Most of the models use various hybrid approaches. Statistical translation approach is completely language independent if we disregard the fact that it requires huge parallel corpus that needs to be split into sentences and words. This paper compares and discusses state-of-the-art statistical machine translation (SMT) models and evaluation methods. Results of statistically-based Google Translate tool for Croatian-English translations are presented and multilevel analysis is given. Three different types of texts are manually evaluated and results are analysed by the χ2-test. 
536 |a Projekt MZOS  |f 130-1300646-0909 
546 |a ENG 
690 |a 2.09 
690 |a 5.04 
690 |a 6.03 
693 |a SMT (statistical machine translation), online, Google Translate, MT, Croatian-English, manual evaluation, fluency, adequacy, χ2-test  |l hrv  |2 crosbi 
693 |a SMT (statistical machine translation), online, Google Translate, MT, Croatian-English, manual evaluation, fluency, adequacy, χ2-test  |l eng  |2 crosbi 
700 1 |a Vičić, Tomislav  |4 aut 
700 1 |9 430  |a Seljan, Sanja  |4 aut 
773 0 |a International Conference The Future of Information Sciences (2 ; 2009) (04.-06.11.2009. ; Zagreb, Hrvatska)  |t 2nd international conference The future of information sciences (INFuture 2009) : Digital resources and knowledge sharing : proceedings  |d Zagreb : Department of Information Sciences, Faculty of Humanities and Social Sciences, University of Zagreb, 2009  |n Stančić, Hrvoje ; Seljan, Sanja ; Bawden, David ; Lasić-Lazić, Jadranka ; Slavić, Aida  |z 978-953-175-355-5  |g str. 319-332 
942 |c RZB  |u 2  |v Recenzija  |z Znanstveni - Predavanje - CijeliRad  |t 1.08 
999 |c 316467  |d 316465