A Review of Statistical and Neural Network Based Hybrid Machine Translators

Machine Translation has become one of the top research interests for a few years. Compared to others, statistical and neural network approaches toward machine translation are performing the best. However, both approaches have advantages over one another. In recent years, few researchers have conducted experiments to create hybrid machine translation systems that combine the strength of statistical and neural network approach to produce a better translation. In this paper, we review all of these research methodologies, datasets, evaluation scores and point out their shortcomings.