Dear list members,
I got several problems when practising step-by-step run through at
http://www.statmt.org/moses_steps.html
1.
It seems fine until the step of use SRILM to build a tri-gram language model
running "tools/srilm/bin/i686/ngram-count -order 3 -interpolate
-kndiscount -unk -text work/lm/news-commentary.lowercased.en -lm
work/lm/news-commentary.lm"
head -n 5 work/lm/news-commentary.lm
The output is correct
But when running
nohup nice $SCRIPTS_ROOTDIR/training/train-model.perl
-scripts-root-dir tools/moses-scripts/scripts-*YYYYMMDD-HHMM*/
-root-dir work -corpus work/corpus/news-commentary.lowercased -f fr -e
en -alignment grow-diag-final-and -reordering msd-bidirectional-fe -lm
8:3:/home/jschroe1/demo/work/lm/news-commentary.lm >&
work/training.out &
The output are fine, except that there is no "*reordering-table.gz"*
but "reordering-table.wbe-msd-bidirectional-fe.gz". Is it correct in
the current moses?
2. In the "Sanity Check Trained Model" step, If I run "echo "c' est
une petite maison ." | tools/moses/moses-cmd/src/moses -f
work/model/moses.ini"
My output is:
----------------------------
Defined parameters (per moses.ini or switch):
config: work/model/moses.ini
distortion-file: 0-0 wbe-msd-bidirectional-fe-allff 6
/home/fangzhong/tools/work/model/reordering-table.wbe-msd-bidirectional-fe.gz
distortion-limit: 6
input-factors: 0
lmodel-file: 0 8 3 /home/fangzhong/tools/work/lm/news-commentary.lm
mapping: 0 T 0
ttable-file: 0 0 0 5 /home/fangzhong/tools/work/model/phrase-table.gz
ttable-limit: 20
weight-d: 0.3 0.3 0.3 0.3 0.3 0.3 0.3
weight-l: 0.5000
weight-t: 0.20 0.20 0.20 0.20 0.20
weight-w: -1
Loading lexical distortion models...have 1 models
Creating lexical reordering...
weights: 0.300 0.300 0.300 0.300 0.300 0.300
Loading table into memory...done.
Start loading LanguageModel
/home/fangzhong/tools/work/lm/news-commentary.lm : [32.000] seconds
/home/fangzhong/tools/work/lm/news-commentary.lm: line 1476: warning:
non-zero probability for <unk> in closed-vocabulary LM
Finished loading LanguageModels : [32.000] seconds
Start loading PhraseTable
/home/fangzhong/tools/work/model/phrase-table.gz : [32.000] seconds
filePath: /home/fangzhong/tools/work/model/phrase-table.gz
Finished loading phrase tables : [32.000] seconds
Start loading phrase table from
/home/fangzhong/tools/work/model/phrase-table.gz : [32.000] seconds
Reading /home/fangzhong/tools/work/model/phrase-table.gz
----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100
****************************************************************************************************
Finished loading phrase tables : [49.000] seconds
IO from STDOUT/STDIN
Created input-output object : [49.000] seconds
Translating line 0 in thread id 0
Translating: c' est une petite maison .
Collecting options took 0.000 seconds
moses: LM/SRI.cpp:152: virtual Moses::LMResult
Moses::LanguageModelSRI::GetValue(const std::vector<const
Moses::Word*>&, const void**) const: Assertion
`(*contextFactor[count-1])[factorType] != __null' failed.
Aborted
-------------------------------
Can anyone please help me why it fails by showing the "moses:
LM/SRI.cpp:152: virtual Moses::LMResult
Moses::LanguageModelSRI::GetValue(const std::vector<const
Moses::Word*>&, const void**) const: Assertion
`(*contextFactor[count-1])[factorType] != __null' failed.
Aborted" error? How can I solve it?
Many thanks
Su
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support
