Hi Andrew,
you should have no problems using filter-pt to prune phrase tabels with
multiple factors.
The program prints quite a lot of status information during its run,
maybe try to check the log? Or post it to the list for us to investigate :-)
Cheers,
Ceslav
on 26.7.2013 19:41 Andrew
Hi Andrew,
filter-pt prunes phrase tables with multiple factors just fine.
Cheers,
Ceslav
on 23.7.2013 22:44 Andrew Vine said the following:
Hi,
I would like to prune some phrase tables following the method
described here..
http://www.statmt.org/moses/?n=Moses.AdvancedFeatures#ntoc19
Could
Hi Benyamin,
to set enviroment variable IRSTLM, you have to call export
IRSLTLM=/home/benyamin/irstlm before any other command that requires
this variable to be set.
Try to run this sequence instead of your single command:
export IRSLTLM=/home/benyamin/irstlm
irstlm/bin/add-start-end.sh
Hello,
I'm reusing code for smoothing from the consolidate tool in one of my
projects and I've noticed that there might be a small bug in Kneser-Ney
discounting implementation:
if (kneserNeyFlag) {
...
if (countEF 2) D = kneserNey_D1;
if (countEF 3) D = kneserNey_D2;
...
}
Shouldn't
willing to share the results of
your experimentation with the relent-filter.
On 01/03/2013 13:30, Česlav Przywara wrote:
Hi all,
I'd like to ask, if anyone have ever tried out the tool for pruning of
phrase table based on Relative Entropy (contrib/relent-filter)? It is
also mentioned
to use the
RELEASE-0.91, or whatever you version you want
On 4 March 2013 09:11, Česlav Przywara ces...@przywara.cz
mailto:ces...@przywara.cz wrote:
Hi Hieu,
If you'll make relent-filter work, I'll be happy to share my results.
Cheers,
Ceslav
on 3.3.2013 12:50 Hieu Hoang
Hi all,
I'd like to ask, if anyone have ever tried out the tool for pruning of
phrase table based on Relative Entropy (contrib/relent-filter)? It is
also mentioned on Advanced Features page:
http://www.statmt.org/moses/?n=Moses.AdvancedFeatures#ntoc23
I wanted to give a try, but didn't manage
Marcin,
did you manage to make sigfilter working?
Cheers,
Ceslav
on 25/06/12 19:37 Marcin Junczys-Dowmunt said the following:
Thanks,
I will take a look.
W dniu 25.06.2012 16:26, Kenneth Heafield pisze:
I uploaded my Frankenstein version: https://github.com/kpu/SALM .
Compile with bjam,
Hi All,
I've discovered that in some cases, when there are multiple alignments
with the most frequent count occuring for a certain phrase pair, the
scorer pick a distinct alignments as the best ones when producing direct
and inverse halves of the phrase table. As a result, for such phrase
Hi Hieu,
if I understand the new parallelization scheme of phrase table *scoring*
correctly, then:
a) --parallel switches on concurrent processing of direct and inverse
phrase table halves
b) --cores N switches on (further) parallelization of each phrase table
half processing (splitting it
Taylor,
are you running 64-bit Ubuntu? Cause I've recently compiled SRILM on my
Ubuntu and probably came across the very same problem. (I don't remember
the filename, but stubs.h sounds familiar to me.)
Anyway, I think your problem might be caused by SRILM being compiled in
32-bit mode
:35, Česlav Przywara wrote:
Hello,
I'm building a translation model using phrase-extract toolset and I have
troubles with phrase scorer. Scoring of extract file consumed almost 43
cpu hours so far and is still running, but there has been no increment
of the output file for last 16 hours.
May
Hello,
I'm building a translation model using phrase-extract toolset and I have
troubles with phrase scorer. Scoring of extract file consumed almost 43
cpu hours so far and is still running, but there has been no increment
of the output file for last 16 hours.
May there be some inconsistency
Hi,
I came across the same problem (using gcc 4.4.5) when compiling
sigtest-filter.
#include cstring in sigtest-filter/filter-pt.cpp solved the issue, but
it would be nice to have it fixed in repository.
Regards,
Ceslav
on 08/03/11 16:46 Hieu Hoang said the following:
ah sorry, added
14 matches
Mail list logo