Hi all,
I’ve done the corpus preparation and language model training with my own data.
However, the training of translation system doesn’t go very well. The error
massage says "Cannot find /opt/mosesdecoder/tools/merge_alignment.py at
/opt/mosesdecoder/scripts/training/train-model.perl line 384."
But they are just at the right place as the following text shows.
I’m using Mgiza instead of the default one on the website.
Both of the Mosesdecoder and MGIZA are installed at the admin’s directory.
fangting@phon:/opt/mosesdecoder$ ls
bin scripts tools
fangting@phon:/opt/mosesdecoder$ cd tools/
fangting@phon:/opt/mosesdecoder/tools$ ls
d4norm merge_alignment.py run.sh sntpostproc.py
force-align-moses-old.sh mgiza snt2cooc symal
force-align-moses.sh mkcls snt2cooc.pl
giza2bal.pl plain2snt snt2coocrmp
hmmnorm plain2snt-hasvcb.py snt2plain
fangting@phon:~/working$ nohup nice $MOSES/scripts/training/train-model.perl
-root-dir train -corpus ~/es-fi/OpenSubtitles2013.es-fi.clean -f es -e fi
-alignment grow-diag-final-and -reordering msd-bidirectional-fe -lm
0:3:$HOME/lm/OpenSubtitles2013.es-fi.blm.fi:8 -mgiza -mgiza-cpus 8
-external-bin-dir $MOSES/tools >& training.out &
[1] 22362
fangting@phon:~/working$ ls
training.out
[1]+ Exit 255 nohup nice
$MOSES/scripts/training/train-model.perl -root-dir train -corpus
~/es-fi/OpenSubtitles2013.es-fi.clean -f es -e fi -alignment
grow-diag-final-and -reordering msd-bidirectional-fe -lm
0:3:$HOME/lm/OpenSubtitles2013.es-fi.blm.fi:8 -mgiza -mgiza-cpus 8
-external-bin-dir $MOSES/tools &> training.out
fangting@phon:~/working$ cat training.out
nohup: ignoring input
Using SCRIPTS_ROOTDIR: /opt/mosesdecoder/scripts
Using multi-thread GIZA
ERROR: Cannot find /opt/mosesdecoder/tools/merge_alignment.py at
/opt/mosesdecoder/scripts/training/train-model.perl line 384.
Best,
Fangting
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support