Hi Christof Pintaske,

Well..Really thanking again for your concern... I was informed yesterday by 
Mr. Barry Haddow that  train-model.perl has been renamed as 
train-factored-phrase-model.perl in the distribution that I have installed.. so 
now resolved the issue...Hoping to install recent version of Moses from svn for 
the final run of my system...... Thanking you...

Regards,
S.Sripirakas.

--- On Mon, 5/24/10, Christof Pintaske <[email protected]> wrote:

From: Christof Pintaske <[email protected]>
Subject: Re: [Moses-support] Use of unfactored training data set in moses???
To: "sripirakas sakthithasan" <[email protected]>
Date: Monday, May 24, 2010, 10:30 AM





  
  


Hi,



I recommend to checkout a recent version of moses from the subversion
repository. That should have the script. Other than that I don't really
know what to do, I'm not involved in the development of moses. If in
doubt, you should check back on the list. Typically Hieu Hoang and
Philipp Koehn know a solution.



best regards

Christof





On 5/23/10 9:31 PM, sripirakas sakthithasan wrote:

  
    
      
        Hi

        

I am sorry to mention that I couldn't still find that train-model.perl anywhere 
in moses
directories. My one is "moses-2010-04-26" which was downloaded from
http://sourceforge.net/projects/mosesdecoder/ very recently. The list
of released files are as follows,

        

        

analysis/README

analysis/sentence-by-sentence.pl

generic/extract-factors.pl

generic/lopar2pos.pl

generic/moses-parallel.pl

generic/multi-bleu.perl

generic/qsub-wrapper.pl

Makefile

README

released-files

training/absolutize_moses_model.pl

training/build-generation-table.perl

training/clean-corpus-n.perl

training/clone_moses_model.pl

training/cmert-0.5/bleu.py

training/cmert-0.5/dataset.py

training/cmert-0.5/log.py

training/cmert-0.5/mert

training/cmert-0.5/enhanced-mert

training/cmert-0.5/reduce-field.pl

training/cmert-0.5/extend-field.pl

training/cmert-0.5/python/psyco/classes.py

training/cmert-0.5/python/psyco/core.py

training/cmert-0.5/python/psyco/__init__.py

training/cmert-0.5/python/psyco/kdictproxy.py

training/cmert-0.5/python/psyco/logger.py

training/cmert-0.5/python/psyco/profiler.py

training/cmert-0.5/python/psyco/_psyco.so

training/cmert-0.5
/python/psyco/support.py

training/cmert-0.5/README

training/cmert-0.5/score-nbest.py

training/mbr/mbr

training/filter-model-given-input.pl

training/filter-and-binarize-model-given-input.pl

training/filter-rule-table.py

training/lexical-reordering/score

training/memscore/memscore

training/zmert-moses.pl

training/mert-moses.pl

training/mert-moses-new.pl

training/phrase-extract/extract

training/phrase-extract/extract-rules

training/phrase-extract/score

training/phrase-extract/consolidate

training/postprocess-lopar.perl

training/reduce_combine.pl

training/combine_factors.pl

training/train-factored-phrase-model.perl

training/symal/symal

training/symal/giza2bal.pl

training/wrappers/parse-de-bitpar.perl

training/wrappers/parse-en-collins.perl

recaser/train-recaser.perl

recaser/recase.perl

recaser/detokenizer.perl

recaser/truecase.perl

recaser/detruecase.perl

recaser/train-tr
uecaser.perl.

        

I followed the installation instructions which appears on
http://www.statmt.org/moses_steps.html and the manual. Thank you
Christof Pintaske for paying your attention on my issue..But still,
looking for your help....Thank you in advance....

        

S.Sripirakas.

        

--- On Wed, 5/19/10, Christof Pintaske <[email protected]>
wrote:

        

From: Christof Pintaske <[email protected]>

Subject: Re: [Moses-support] Use of unfactored training data set in
moses???

To: [email protected]

Date: Wednesday, May 19, 2010, 9:43 AM

          

           where did you get your Moses
installation from? "train-model.perl"
should be in moses/bin/scripts-*/training . At least it has always been
there for me. If that's not the case then you may want to check the
source or checkout a new version from the repository. 

          

hope that helps

Christof

          

          
            
              
                
                  Dear All,

                  

I am doing a research on the development of statistical translation
system for Sri Lankan local languages (Sinhala and Tamil). The
available corpus is unfactored and it was created by me.. So, I would
like to know whether the script found in
moses-scripts/scripts-timestamp/training/train-factored-phrase-model.perl
is
suitable for the training. The manual on "Moses use" specifies a
script called "train-model.perl" for unfactored model training, which I
was unable to locate. Expecting your help as soon as possible. I am
really thanking your help to solve the above issue.

                  

Thank you. 

                  
                
              
            
            

            
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support
  
          
          

          
          

-----Inline Attachment Follows-----

          

          _______________________________________________

Moses-support mailing list

          [email protected]

          http://mailman.mit.edu/mailman/listinfo/moses-support

          
        
        
      
    
  
  




 



      
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to