I have a question on decoding with multiple decoding paths. Can the various 
decoding paths be mixed in the final complete hypothesis or does the score of 
one decoding path compete with the one from the others?

I use different TMs in different decoding paths and I have seen that my output 
has scores set for all of them for a given sentence. This suggests that the 
final hypothesis uses options from both paths but is that really the case?

Another question: Can I use factors in lattice input? Is it even possible to 
have XML markup in input word lattices?

Thanks!
Jörg



_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to