Hi Yared
Try to use absolute paths wherever possible.
Also, you appear to have SCRIPTS_ROOTDIR set to mose/moses-
scripts/scripts-20110409-0748. Does this path still exist?
cheers - Barry
On Sunday 22 Apr 2012 07:58:43 Yared Mekuria wrote:
> Hello Barry and Sara, Thank you for your help.
> I clean tokenize and lowrer case the corpus. and I use train-model.perl up
> to date version and the last problem
> is solved. but after long time processing it says
>
> ==========================================================
>
> Entire Training took: 414 seconds
> Program Finished at: Sat Apr 21 13:43:12 2012
>
> ==========================================================
> Executing: rm -f works/giza.en-cy/en-cy.A3.final.gz
> Executing: gzip works/giza.en-cy/en-cy.A3.final
> (3) generate word alignment @ Sat Apr 21 13:43:12 EDT 2012
> Combining forward and inverted alignment from files:
> works/giza.cy-en/cy-en.A3.final.{bz2,gz}
> works/giza.en-cy/en-cy.A3.final.{bz2,gz}
> Executing: mkdir -p works/model
> Executing: mose/moses-scripts/scripts-20110409-0748//training/symal/
> giza2bal.pl -d "gzip -cd works/giza.en-cy/en-cy.A3.final.gz" -i "gzip -cd
> works/giza.cy-en/cy-en.A3.final.gz"
>
> |mose/moses-scripts/scripts-20110409-0748//training/symal/symal
>
> -alignment="grow" -diagonal="yes" -final="yes" -both="yes" >
> works/model/aligned.grow-diag-final-and
> sh: mose/moses-scripts/scripts-20110409-0748//training/symal/giza2bal.pl:
> not found
> sh: mose/moses-scripts/scripts-20110409-0748//training/symal/symal: not
> found
> Exit code: 127
> ERROR: Can't generate symmetrized alignment file
>
> I don't know why it use two forward slash "//training/symal/giza2bal.pl"
> to refer to symal directory
> is there and code to be edited?
>
> On Sat, Apr 21, 2012 at 3:42 PM, Barry Haddow
<[email protected]>wrote:
> > Hi Yared
> >
> > GIZA++ is giving you a segmentation fault, which doesn't usually happen.
> > Maybe
> > there's some odd characters in your data, or it's not sentence aligned
> > properly?
> >
> > I notice that you're using quite an old version of Moses (the training
> > script
> > is now called train-model.perl) so it would be worth running with
> > up-to-date
> > Moses and GIZA++
> >
> > cheers - Barry
> >
> > On Saturday 21 Apr 2012 13:18:48 Yared Mekuria wrote:
> > > Hello there, I am using sentences in Welsh and English to train. I
> > > tokenized, lower cased and build language model but when I try to train
> > > Phrase model using the command below
> > >
> > > nohup nice
> >
> > mose/moses-scripts/scripts-20120409-0748/training/train-factored-phrase-m
> >od
> >
> > > el.perl -scripts-root-dir mose/moses-scripts/scripts-20110409-0748/
> > > -root-dir work -corpus work/corpus/pnaw.lowercased -f cy -e en
> >
> > -alignment
> >
> > > grow-diag-final-and -reordering msd-bidirectional-fe -lm
> > > 1:3:/home/admin1/work/lm/pnaw-full.en.blm >& work/training.out &
> > >
> > > and when I execute the following command
> > >
> > > tail -f work/training.out
> > >
> > > It says the following error
> > >
> > > manlexmaxmultiplicity = 20 ()
> > > maxfertility = 10 (maximal fertility for fertility models)
> > > p0 = 0.999 (fixed value for parameter p_0 in IBM-3/4 (if negative then
> >
> > it
> >
> > > is determined in training))
> > > pegging = 0 (0: no pegging; 1: do pegging)
> > >
> > > reading vocabulary files
> > > Reading vocabulary file from:work/corpus/en.vcb
> > > Reading vocabulary file from:work/corpus/cy.vcb
> > >
> > > ERROR: Execution of: /home/admin1/mose/bin/GIZA++ -CoocurrenceFile
> > > work/giza.cy-en/cy-en.cooc -c work/corpus/cy-en-int-train.snt -m1 5 -m2
> > > 0 -m3 3 -m4 3 -model1dumpfrequency 1 -model4smoothfactor 0.4 -nodumps 1
> > > -nsmooth 4 -o work/giza.cy-en/cy-en -onlyaldumps 1 -p0 0.999 -s
> > > work/corpus/en.vcb -t work/corpus/cy.vcb
> > > died with signal 11, without coredump
> > >
> > > anyone with suggestion please help me.
> > > Thank you.
>
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support
