Hi,
the translation option expansion of factored models may explode in the
setup that you use above
(there are many possible lemma and pos mappings, and the product of
them is explored during
your first two decoding steps).
You could remedy this by:
- use shorter phrase lengths
- use tighter t-ta
Hi,
there are only minimal difference in the training of hierarchical and
phrase-based systems.
The easiest to find out what to do is to use experiment.perl, as described here:
http://www.statmt.org/moses/?n=FactoredTraining.EMS#ntoc7
If you want to get theoretical background then the following
Dear all,
I am looking for a good document about how to train and run moses for
hierarchical phrase-based translations . Of-course that the moses
manual is good , but i am looking for a more straight-forward
document.
tnx in advance
--
S.Farzi, Ph.D. Student
Natural Language Proc
Dear Sir/Madam,
I've been trying to use Lattice Minimum Bayes Risk decoding in Moses,
by adding the flag "-lminimum-bayes-risk".
What then normally happens is the decoder crashes,
since the file /mosesdecoder/moses-chart-cmd/Main.cpp
contains the line CHECK(!staticData.UseMBR());
This assertion b
