hello

I just noticed that moses seems to be loading the phrase table two times :

Start loading PhraseTable /global/markov/raybauds/MODELS/GIZA-MOSES-EUROPARL-
WMT09/fr-en/model/phrase-table.gz : [13.000] seconds
filePath: /global/markov/raybauds/MODELS/GIZA-MOSES-EUROPARL-WMT09/fr-
en/model/phrase-table.gz
Finished loading phrase tables : [13.000] seconds
Start loading phrase table from /global/markov/raybauds/MODELS/GIZA-MOSES-
EUROPARL-WMT09/fr-en/model/phrase-table.gz : [13.000] seconds

the file is exactly the same the two times. Is that normal? It does not seem to 
be the case on the example given on 
http://www.statmt.org/moses/?n=Moses.Tutorial

You'll find my moses.ini attached. I obtained the similar behavior with 
different configuration files.

Maybe it's nothing, maybe it has always been that way, I can't remember. I 
just find it strange. I'm currently running moses compiled from the last svn 
version.

regards,

-- 
Sylvain Raybaud
# MERT optimized configuration
# decoder /usr/local/bin/moses
# BLEU 0.230684 on dev /home/sylvain/GMR/DATA/EUROPARL/test/en-fr.clean.fr
# We were before running iteration 10
# finished Fri Feb 18 05:08:51 CET 2011
### MOSES CONFIG FILE ###
#########################

# input factors
[input-factors]
0

# mapping steps
[mapping]
0 T 0

# translation tables: table type (hierarchical(0), textual (0), binary (1)), 
source-factors, target-factors, number of scores, file 
# OLD FORMAT is still handled for back-compatibility
# OLD FORMAT translation tables: source-factors, target-factors, number of 
scores, file 
# OLD FORMAT a binary table type (1) is assumed 
[ttable-file]
0 0 0 5 
/global/markov/raybauds/MODELS/GIZA-MOSES-EUROPARL-WMT09/fr-en/model/phrase-table.gz

# no generation models, no generation-file section

# language models: type(srilm/irstlm), factors, order, file
[lmodel-file]
0 0 5 /home/sylvain/GMR/MODELS/GIZA-MOSES-EUROPARL-WMT09/en.lm


# limit on how many phrase translations e for each phrase f are loaded
# 0 = all elements loaded
[ttable-limit]
20

# distortion (reordering) weight
[weight-d]
0.157708

# language model weights
[weight-l]
0.164514


# translation model weights
[weight-t]
0.084417
0.127029
0.215193
0.11591
0.0543859

# no generation models, no weight-generation section

# word penalty
[weight-w]
-0.080843

[distortion-limit]
6
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to