The tree-to-string model is faster for decoding, compared to hiero model,
and much faster compared to string-to-tree.
therefore, imo, you don't need to prune because pruning always causes
search errors.
if you mean filtering by input sentences to get rid of rules you know will
never apply (ie.
Hello,
I use a training corpus to build my translation system.
But i founf in this corpus some HTML tags like for instance :
and i apos;m going to start with this one : if momma ain apos;t happy ,
ain apos;t nobody happy .
Should i have to elliminate this? or keep them?
Thank you in advance
Marcin Junczys-Dowmunt junczys@... writes:
Hi list,
If I am not mistaken, there is currently no functionality to prune
tree-to-string rule tables. Do you think it makes sense to use filter-pt
for hierarchical rules instead, for instance by replacing category
symbols with the generic
Ah, perfect. I somehow firmly believed this only works for the
non-syntactic hierarchical models. Thanks!
Best,
Marcin
W dniu 24.07.2013 15:19, Rico Sennrich pisze:
Marcin Junczys-Dowmunt junczys@... writes:
Hi list,
If I am not mistaken, there is currently no functionality to prune
yes, copy PhraseDictionaryDynSuffixArray, or indeed, your own
PhraseDictionaryCompact.
there's some docs on adding feature functions.
http://www.statmt.org/moses/?n=Moses.FeatureFunctions
it should be easier than a year ago when you added PhraseDictionaryCompact
On 24 July 2013 13:29, Marcin
Thanks, I am mainly interested in reusing most of the score calculation
methods in BilingualDynSuffixArray.* and was looking for an easy way to
do that. Now that I have inspected the code for a while I see there is
no easy way :)
W dniu 24.07.2013 15:29, Hieu Hoang pisze:
yes, copy
You shouldnt keep them: the and ; would be tokenized and pollute
your sentences.
There are tools to convert them, at least a perl module I think,
search about html decoding. They are called html entities, not tags.
On Wed, Jul 24, 2013 at 2:16 PM, Cyrine NASRI cyrine.na...@gmail.com wrote:
Hi, Marcin,
this could be quite useful (although we did not see any improvements in our
experiments, see our WMT(12,11?) paper Selecting Data in EN-CS Translation).
It can be useful to index a different factor than the factors that one
eventually wants to use in translation. So the config
Hi Ondrej,
I do not aim at that much at quality improvement, just want to have a
very flexible data structure. I am planning a series of experiments
where cruel and twisted things will be done to the source language and
thought that might be a good way to speed up experimenting without
having
Hello,
Are there any quick ways to remove HTML tags and align sentences for Arabic
English without having to go through about 45000 lines manually?
___
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
Hi All,
I try to do a training using Berkeley Word Aligner but I have errors in
TRAINING_run-berkeley.1 or TRAINING_process-berkeley.1 steps becaouse the
system cannot find the 'usr/local/share/java/bin/java'.
I replaced the '/usr/local/share/java/bin/java' with '/usr/bin/java' or
'java' in
I think you asked this question before. I check and was pretty sure it
works.
How exactly are you running Moses? Can you send me your config files and
any other info that you think might be useful to debug this issue.
On 23 July 2013 07:46, Li Xiang lixiang@gmail.com wrote:
At MERT stage,
from the comment on line 48 in
https://github.com/moses-smt/mosesdecoder/blob/master/mert/ScorerFactory.cpp
it looks like it's been implmented already. Other people may know more
about it than me
On 18 July 2013 16:09, Felipe Sánchez Martínez fsanc...@dlsi.ua.es wrote:
Hi all,
Before going
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
I find the following code in the moses/TranslationOptionCollection.cpp
isDigit = s.find_first_of(“0123456789”);
if (isDigit == 1)
isDigit = 1;
else
isDigit == 0;
But nearly the same code segment appears in the moses/ChartParser.cpp
isDigit = s.find_first_of(“0123456789”);
if (isDigit ==
15 matches
Mail list logo