Try statistical MT, e.g. Moses http://www.statmt.org/moses/index.php?n=Main.HomePage Might be fairer too, given that we probably don't have the ten million words of parallel corpora it takes for an NMT system to beat SMT
On Mon, May 27, 2019 at 12:16 PM Sevilay Bayatlı <[email protected]> wrote: > Hi, > > I need to compare apetium-ambiguous result with similar state-of-the-art > systems, I have compared it with OpenNMT, do you have any suggestions? > > Best wishes, > Sevilay > > > _______________________________________________ > Apertium-stuff mailing list > [email protected] > https://lists.sourceforge.net/lists/listinfo/apertium-stuff >
_______________________________________________ Apertium-stuff mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/apertium-stuff
