In this paper, an extended combined approach of phrase based statisticalmachine translation (SMT), example based MT (EBMT) and rule based MT (RBMT) isproposed to develop a novel hybrid data driven MT system capable ofoutperforming the baseline SMT, EBMT and RBMT systems from which it is derived.In short, the proposed hybrid MT process is guided by the rule based MT aftergetting a set of partial candidate translations provided by EBMT and SMTsubsystems. Previous works have shown that EBMT systems are capable ofoutperforming the phrase-based SMT systems and RBMT approach has the strengthof generating structurally and morphologically more accurate results. Thishybrid approach increases the fluency, accuracy and grammatical precision whichimprove the quality of a machine translation system. A comparison of theproposed hybrid machine translation (HTM) model with renowned translators i.e.Google, BING and Babylonian is also presented which shows that the proposedmodel works better on sentences with ambiguity as well as comprised of idiomsthan others.
展开▼
