Hi, one recently proposed successful strategy is to first translate the source sentences in the parallel corpus with the rule-based system (in this case Apertium) and then build a statistical system from the rule-based output to the correct translation in the parallel corpus.
This is referred to as statistical post-editing. Simard, Michel and Ueffing, Nicola and Isabelle, Pierre and Kuhn, Roland(2007): Rule-Based Translation with Statistical Phrase-Based Post-Editing, Proceedings of the Second Workshop on Statistical Machine Translation. http://www.aclweb.org/anthology/W/W07/W07-2028.pdf -phi On Fri, Mar 14, 2014 at 2:39 AM, Kalyani Baruah <kajubarua...@gmail.com> wrote: > > hii, I want to make a system by joining moses and apertium tool .is it > possible to combine them into a hybrid machine. > > > > Regards, > > > > Kalyanee Kanchan Baruah > Institute of Science and Technology, > Gauhati University,Guwahati,India > Phone- +91-9706242124 > > _______________________________________________ > Moses-support mailing list > Moses-support@mit.edu > http://mailman.mit.edu/mailman/listinfo/moses-support > _______________________________________________ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
