Injected linguistic tags to improve phrase based SMT

This paper presents Injected Tags (ITs) approach, that improves the phrase based statistical machine translation (PBSMT) approach. This Injected Tags approach has been applied to ¿English into Arabic translation¿. This approach is language independent and can be used with any language pair. It has shown considerable improvement of the translation quality of at least 13% increase of BLEU score. The approach has been evaluated and has been compared with several online Machine Translation (MT) services. The experiments reveal that the results achieved by this approach considered significant enhancements over PBSMT.