Experiments with Small-size Corpora in CBMT
Monica Gavrila, Natalia Elita · 2011
There is no doubt that in the last couple of years corpus-based machine translation (CBMT) approaches have been in focus. Each of the approaches has its advantages and disadvantages. Therefore, hybrid approaches have been developed. This paper presents a comparative study of CBMT approaches, using three types of systems: a statistical MT (SMT) system, an example-based MT (EBMT) system and a hybrid (EBMT-SMT) system. We considered for our experiments three languages, from different language families: Romanian, German and English. Two different types of corpora have been used: while the first is manually created, the latter is automatically built.