.Bold { font-weight: bold; }
.Title { font-weight: bold; font-size: 18px; color: #cc3300; }
.Code { border: #8b4513 1px solid; padding-right: 5px; padding-left: 5px;color:
#000066; font-family: 'Courier New' , Monospace;background-color: #ff9933; }
Hi, everyone,I've got a question about factored training.First, do I have to
modify internal sources of Moses if I perform alignment as below,Foreign
language : Word|POSTarget language : Word|POSalignment : 0-0, 1-0, 1-1input in
decoding... : Word|POS Word|POS Word|POS .....At first I thought Moses
automatically tells factor 1 from factor 2, but it seems not.Second, if I add a
factor while corpus size is fixed, am I sure to see the increase in accuracy.Is
this completely different case from COD(curse of dimensionality) problem?
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support
