Hi,

I was adding a new feature function in Moses (https://github.com/KonceptGeek/mosesdecoder/blob/master/moses/FF/CoarseBiLM.cpp). It works fine when I test it for 1-2 sentences, but when I’m trying to tune my parameters, I’m getting segmentation faults or sometimes it is bad_alloc. Following was one of the commands that was executed during the tuning process which caused the Segmentation Fault or bad_alloc:

moses -threads 40 -v 0 -config filtered/moses.ini -weight-overwrite 'CoarseLM100= 0.075758 LM0= 0.075758 CoarseBiLMNotClustered= 0.075758 WordPenalty0= -0.151515 PhrasePenalty0= 0.030303 CoarseBiLMClustered= 0.075758 TranslationModel0= 0.030303 0.030303 0.030303 0.030303 Distortion0= 0.045455 CoarseLM1600= 0.075758 LexicalReordering0= 0.045455 0.045455 0.045455 0.045455 0.045455 0.045455' -n-best-list run1.best100.out 100 distinct -input-file tune.word.lc.cn

The log is enclosed in this email.

Any pointers would be very useful.

Thanks,
Jasneet

Loading the LM will be faster if you build a binary file.
Reading 
/cs/natlang-projects/jasneet/Data/BilingEmbeddings/mt/lm/english.giga5.lm.gz
----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100
*The ARPA file is missing <unk>.  Substituting log10 probability -100.000.
***************************************************************************************************
Loading table into memory...done.
Key: tgtWordToClusterId
LoadManyToOneMap Value: 
/cs/natlang-projects/jasneet/Data/BilingEmbeddings/outputs-clusters/mkcls/cn-en-roland-generic-big/clusters/clusters.400.en
Key: srcWordToClusterId
LoadManyToOneMap Value: 
/cs/natlang-projects/jasneet/Data/BilingEmbeddings/outputs-clusters/mkcls/cn-en-roland-generic-big/clusters/clusters.400.cn
Key: bitokenToBitokenId
LoadManyToOneMap Value: 
/cs/natlang-projects/jasneet/Data/BilingEmbeddings/outputs-clusters/mkcls/cn-en-roland-generic-big/corpus/corpus.bitoken.400.class.cnen.tags
Key: bitokenIdToClusterId
LoadManyToOneMap Value: 
/cs/natlang-projects/jasneet/Data/BilingEmbeddings/outputs-clusters/mkcls/cn-en-roland-generic-big/clusters/clusters.400.bitoken
Key: lm
Key: ngrams
Key: tgtWordToClusterId
LoadManyToOneMap Value: 
/cs/natlang-projects/jasneet/Data/BilingEmbeddings/outputs-clusters/mkcls/cn-en-roland-generic-big/clusters/clusters.400.en
Key: srcWordToClusterId
LoadManyToOneMap Value: 
/cs/natlang-projects/jasneet/Data/BilingEmbeddings/outputs-clusters/mkcls/cn-en-roland-generic-big/clusters/clusters.400.cn
Key: bitokenToBitokenId
LoadManyToOneMap Value: 
/cs/natlang-projects/jasneet/Data/BilingEmbeddings/outputs-clusters/mkcls/cn-en-roland-generic-big/corpus/corpus.bitoken.400.class.cnen.tags
Key: lm
Key: ngrams
Key: tgtWordToClusterId
LoadManyToOneMap Value: 
/cs/natlang-projects/jasneet/Data/BilingEmbeddings/outputs-clusters/mkcls/cn-en-roland-generic-big/clusters/clusters.100.en
Key: lm
Key: ngrams
Key: tgtWordToClusterId
LoadManyToOneMap Value: 
/cs/natlang-projects/jasneet/Data/BilingEmbeddings/outputs-clusters/mkcls/cn-en-roland-generic-big/clusters/clusters.1600.en
Key: lm
Key: ngrams
terminate called after throwing an instance of 'std::bad_alloc'
  what():  std::bad_alloc
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to