Dear all,
I hope that this is not too stupid a question, and that it hasn't been asked
recently.
In the MOSES EMS, when running experiments the phrase table is automatically
reduced to only those phrases that actually occur in the respective dev/test
set. Obviously this saves a lot of memory
this can be done, but it tends to not save much space. also it does
not help deal with OOVs, which the language model can still score even
though they are not in the parallel set.
if you are worried about saving space then you should either look at
KenLM or RandLM
Miles
On 24 November 2011
Hi all,
is there a specific reason/obstacle that METEOR is not available for MERT?
Cheers,
Christian
Christophe Servan christophe.ser...@gmail.com hat am 24. November 2011 um
19:02 geschrieben:
Hi Wilker,
I confirm there is currently no scorer for METEOR in MERT.
Do you plan do
Hi,
Maybe the lack of time ;-)
Christophe
Le 24/11/2011 19:10, Christian Federmann a écrit :
Hi all,
is there a specific reason/obstacle that METEOR is not available for MERT?
Cheers,
Christian
Christophe Servanchristophe.ser...@gmail.com hat am 24. November 2011 um
Ah yes... the usual suspect ;)
Might be worth implementing though... let's see.
Cheers,
Christian
Christophe Servan christophe.ser...@gmail.com hat am 24. November 2011 um
19:19 geschrieben:
Hi,
Maybe the lack of time ;-)
Christophe
Le 24/11/2011 19:10, Christian Federmann a
Hi all,
I've got a quick question regarding the tuning of hierarchical phrase-based
models. When calling mert, my terminal outputs an error I can't find in the
mailing lists:
main::create_extractor_script() called too early to check prototype at
./mert-moses.pl line 666
The script didn't stop