1.Is there actually a module called Moses Web-based? Where can I find any
tutorial to set it up?
2. How does Moses Web-based work? Does it load the phrase tables and
language models once the server starts, and use the same tables without
re-loading them over and over?
Thanks
Hi all, i am trying to use the Lattice decoding (with input-type=2 ie
real word lattice not confusion network) and i think i identified some
issues with the way unknown words are dealt with:
If i understand correctly, the weigth associated to the penalty
associated to a given edge of the lattice
I think that the problem with unknow words is that both the feature
weight and the feature value are fixed: (1 for the weight, -100 for the
value of the feature)
JB
Miles Osborne a écrit :
Remember that features also have weights (in addition to their
values). For your constant feature
Hi, Vineet,
thanks for your reply, but I think i use
/moses/scripts/training/clean-corpus-n.perl test2 ch en 0 1 80
to clean the corpus already, and I checked it and it seems to be sentence
aligned.
and I checked the error information, and it seems that what it said
mismatch are actually
Hi -
We switched to using IRSTLM recently, in order to build bigger
language models. I am starting to think, however, that the entire
model is still being loaded into memory. Here's part of what Moses
prints out now:
Start loading LanguageModel /net/tidesserver/tidesserver_raid7/clasr/