Hi, If you don't need all score components of a phrase table, the easiest way to get rid of them is to set the scaling factors for the undesired phrase table feature function components to 0 before tuning, and ask the optimizer to ignore them. The feature function configuration parameter "tuneable-components" can be used to tune only selected components of the feature function. http://permalink.gmane.org/gmane.comp.nlp.moses.user/12464
I'm using this quite frequently with MIRA. It's conceivable that it won't work with MERT, though, since maybe this combination was never tested. Alternatively, remove any undesired score columns from your phrase table. The latter approach has advantages as well. E.g., that way it's less likely to end up with unnoticed mistakes in the configuration files. As always, check the content of your log files and any intermediate files to avoid unexpected behavior. If you decide to give "tuneable -components" a try, it will be easy to figure out whether it does what it's supposed to do by just inspecting the tuned weights. If you end up using only a single feature function with one score component (assuming that you get rid of UnknownWordPenalty in one way or another), then you won't have to tune. There's nothing to interpolate if there's only one feature. The only thing you'll have to think about is whether to set its scaling factor to a negative or to a positive value. Search in Moses does argmax, some other decoders may implement argmin. Cheers, Matthias On Wed, 2016-01-13 at 15:20 +0000, Read, James C wrote: > Thanks, > > and if I wanted Moses to use one feature of TM alone I'm guessing > there's no way to do this other than zeroing out the undesired TM > features? > > > From: Hieu Hoang <[email protected]> > Sent: Wednesday, January 13, 2016 3:05 PM > To: Read, James C > Cc: Moses Support > Subject: Re: [Moses-support] Tuning with no language model > > you can delete all feature functions except for the > UnknownWordPenalty. In the current moses, thats hardcoded into > decoding. So be my guest and delete away! > > Hieu Hoang > http://www.hoang.co.uk/hieu > > On 13 January 2016 at 15:02, Read, James C <[email protected]> > wrote: > > OK, looks like it's running. Probably won't be able to see if it > > generates useful weights until tomorrow. Thanks. > > > > As a side line of thought. I was wondering how many lines of > > configuration I could get away with deleting? How would Moses > > behave if I were to delete the lexical reordering lines? The > > distortion? The word penalty? The phrase penalty? > > > > My goal is to get Moses to choose the best translation with > > reference to the translation model only. > > > > If I delete these other configuration lines will Moses use defaults > > for these other options or completely disable their operation > > leaving just the TM? > > > > > > From: Hieu Hoang <[email protected]> > > Sent: Wednesday, January 13, 2016 2:51 PM > > > > To: Read, James C > > Cc: Moses Support > > Subject: Re: [Moses-support] Tuning with no language model > > > > ok. The mert script create a temporary directory every time you run > > it. By default it's named > > mert-work > > Since you ran mert with an incorrect moses.ini previously, it may > > have polluted the temporary directory and cause problem now. > > > > You should find this temporary directory and delete it before > > running mert again. > > > > ps ALL directories must be absolute, eg ../tuning_data/true.bg > > > > > > Hieu Hoang > > http://www.hoang.co.uk/hieu > > > > On 13 January 2016 at 14:45, Read, James C <[email protected]> > > wrote: > > > > > > /media/bigdata/jcread/llv/data/europarlv7/raw/aligned/bg > > > -en/training_data$ > > > /media/bigdata/jcread/3rd_party_software/mosesdecoder/scripts/tra > > > ining/mert-moses.pl -no-filter-phrase-table > > > ../tuning_data/true.bg ../tuning_data/true.en > > > /media/bigdata/jcread/3rd_party_software/mosesdecoder/bin/moses > > > /media/bigdata/jcread/llv/data/europarlv7/raw/aligned/bg > > > -en/training_data/binarised/moses-tm.ini --mertdir > > > /media/bigdata/jcread/3rd_party_software/mosesdecoder/bin/ > > > > > > with absolute path to moses-tm.ini does not resolve the problem. > > > Still get the same error. > > > > > > From: Read, James C > > > Sent: Wednesday, January 13, 2016 2:40 PM > > > To: Hieu Hoang > > > > > > Cc: Moses Support > > > Subject: Re: [Moses-support] Tuning with no language model > > > > > > This is what I get when I run the same command as you: > > > > > > LexicalReordering0= 0.300000 0.300000 0.300000 0.300000 0.300000 > > > 0.300000 > > > Distortion0= 0.300000 > > > UnknownWordPenalty0 UNTUNEABLE > > > WordPenalty0= -1.000000 > > > PhrasePenalty0= 0.200000 > > > TranslationModel0= 0.200000 0.200000 0.200000 0.200000 > > > > > > Looks just like your output. However, this is what I get when I > > > run the mert script with the following command: > > > > > > /media/bigdata/jcread/llv/data/europarlv7/raw/aligned/bg > > > -en/training_data$ > > > /media/bigdata/jcread/3rd_party_software/mosesdecoder/scripts/tra > > > ining/mert-moses.pl -no-filter-phrase-table > > > ../tuning_data/true.bg ../tuning_data/true.en > > > /media/bigdata/jcread/3rd_party_software/mosesdecoder/bin/moses > > > binarised/moses-tm.ini --mertdir > > > /media/bigdata/jcread/3rd_party_software/mosesdecoder/bin/ > > > > > > Loading UnknownWordPenalty0 > > > Loading WordPenalty0 > > > Loading PhrasePenalty0 > > > Loading LexicalReordering0 > > > Loading Distortion0 > > > Loading TranslationModel0 > > > LM0 > > > The following weights have no feature function. Maybe incorrectly > > > spelt weights: LM0,Exit code: 1 > > > The decoder died. CONFIG WAS -weight-overwrite 'PhrasePenalty0= > > > 0.043478 WordPenalty0= -0.217391 TranslationModel0= 0.043478 > > > 0.043478 0.043478 0.043478 Distortion0= 0.065217 LM0= 0.108696 > > > LexicalReordering0= 0.065217 0.065217 0.065217 0.065217 0.065217 > > > 0.065217' > > > > > > > > > > > > > > > From: Hieu Hoang <[email protected]> > > > Sent: Wednesday, January 13, 2016 2:27 PM > > > To: Read, James C > > > Cc: Moses Support > > > Subject: Re: [Moses-support] Tuning with no language model > > > > > > looks fine to me. This is what I get when I used it to run > > > # $MOSES_DIR/bin/moses -f moses.ini -show-weights > > > .... > > > LexicalReordering0= 0.300000 0.300000 0.300000 0.300000 0.300000 > > > 0.300000 > > > Distortion0= 0.300000 > > > UnknownWordPenalty0 UNTUNEABLE > > > WordPenalty0= -1.000000 > > > PhrasePenalty0= 0.200000 > > > TranslationModel0= 0.200000 0.200000 0.200000 0.200000 > > > > > > Double check that the moses.ini file you sent me is truly what > > > you're using. > > > > > > To be sure, you MUST use absolute paths for all file names, ie. > > > not > > > binarised/moses-tm.ini > > > but > > > /media/bigdata/whatever/binarised/moses-tm.ini > > > > > > On 13/01/16 14:16, Read, James C wrote: > > > > ######################### > > > > ### MOSES CONFIG FILE ### > > > > ######################### > > > > > > > > # input factors > > > > [input-factors] > > > > 0 > > > > > > > > # mapping steps > > > > [mapping] > > > > 0 T 0 > > > > > > > > [distortion-limit] > > > > 6 > > > > > > > > # feature functions > > > > [feature] > > > > UnknownWordPenalty > > > > WordPenalty > > > > PhrasePenalty > > > > PhraseDictionaryCompact name=TranslationModel0 num-features=4 > > > > path=/media/bigdata/jcread/llv/data/europarlv7/raw/aligned/bg > > > > -en/training_data/binarised/phrase-table input-factor=0 output > > > > -factor=0 > > > > LexicalReordering name=LexicalReordering0 num-features=6 > > > > type=wbe-msd-bidirectional-fe-allff input-factor=0 output > > > > -factor=0 > > > > path=/media/bigdata/jcread/llv/data/europarlv7/raw/aligned/bg > > > > -en/training_data/binarised/reordering-table > > > > Distortion > > > > > > > > # dense weights for feature functions > > > > [weight] > > > > # The default weights are NOT optimized for translation > > > > quality. You MUST tune the weights. > > > > # Documentation for tuning is here: > > > > http://www.statmt.org/moses/?n=FactoredTraining.Tuning > > > > > > > > Moses - FactoredTraining/Tuning www.statmt.org > > > > Tuning. Overview. During decoding, Moses scores translation > > > > hypotheses using a linear model. In the traditional approach, > > > > the features of the model are the ... > > > > > > > > UnknownWordPenalty0= 1 > > > > WordPenalty0= -1 > > > > PhrasePenalty0= 0.2 > > > > TranslationModel0= 0.2 0.2 0.2 0.2 > > > > LexicalReordering0= 0.3 0.3 0.3 0.3 0.3 0.3 > > > > Distortion0= 0.3 > > > > > > > > /media/bigdata/jcread/3rd_party_software/mosesdecoder/scripts/t > > > > raining/mert-moses.pl -no-filter-phrase-table > > > > ../tuning_data/true.bg ../tuning_data/true.en > > > > /media/bigdata/jcread/3rd_party_software/mosesdecoder/bin/moses > > > > binarised/moses-tm.ini --mertdir > > > > /media/bigdata/jcread/3rd_party_software/mosesdecoder/bin/ > > > > > > > > > > > > From: Hieu Hoang <[email protected]> > > > > Sent: Wednesday, January 13, 2016 2:05 PM > > > > To: Read, James C > > > > Cc: Moses Support > > > > Subject: Re: [Moses-support] Tuning with no language model > > > > > > > > please show me the EXACT moses.ini and command that you use. > > > > > > > > > > > > > > > > > > > > Hieu Hoang > > > > http://www.hoang.co.uk/hieu > > > > > > > > On 13 January 2016 at 14:04, Read, James C <[email protected]> > > > > wrote: > > > > > So now I get the following error: > > > > > > > > > > > > > > > Loading UnknownWordPenalty0 > > > > > Loading WordPenalty0 > > > > > Loading PhrasePenalty0 > > > > > Loading LexicalReordering0 > > > > > Loading Distortion0 > > > > > Loading TranslationModel0 > > > > > LM0 > > > > > The following weights have no feature function. Maybe > > > > > incorrectly spelt weights: LM0,Exit code: 1 > > > > > > > > > > I didn't get this error without deleting LM0 line. > > > > > > > > > > From: Hieu Hoang <[email protected]> > > > > > Sent: Wednesday, January 13, 2016 1:58 PM > > > > > > > > > > To: Read, James C; Moses Support > > > > > Subject: Re: [Moses-support] Tuning with no language model > > > > > > > > > > there lies your problem. There's a weight for a non-existant > > > > > feature function > > > > > > > > > > On 13/01/16 13:57, Read, James C wrote: > > > > > > no > > > > > > > > > > > > > > > > > > From: Hieu Hoang <[email protected]> > > > > > > Sent: Wednesday, January 13, 2016 1:56 PM > > > > > > To: Read, James C; Moses Support > > > > > > Subject: Re: [Moses-support] Tuning with no language model > > > > > > > > > > > > did you delete the line > > > > > > LM0= 0.5 > > > > > > too? > > > > > > > > > > > > On 13/01/16 13:53, Read, James C wrote: > > > > > > > The following command works fine for when a language > > > > > > > model is specified. Deleting the line KENLM lazyken=0 > > > > > > > name=LM0 factor=0 path=$PWD/blm.en order=3 > > > > > > > causes the script to fail with error: > > > > > > > > > > > > > > ERROR: Failed to run '/pathtomoses/mosesdecoder/bin/moses > > > > > > > -config /pathtodata/binarised/moses.ini -show-weights'. > > > > > > > at /pathtomoses/mosesdecoder/scripts/training/mert > > > > > > > -moses.pl line 1744. > > > > > > > > > > > > > > ######################### > > > > > > > ### MOSES CONFIG FILE ### > > > > > > > ######################### > > > > > > > > > > > > > > # input factors > > > > > > > [input-factors] > > > > > > > 0 > > > > > > > > > > > > > > # mapping steps > > > > > > > [mapping] > > > > > > > 0 T 0 > > > > > > > > > > > > > > [distortion-limit] > > > > > > > 6 > > > > > > > > > > > > > > # feature functions > > > > > > > [feature] > > > > > > > UnknownWordPenalty > > > > > > > WordPenalty > > > > > > > PhrasePenalty > > > > > > > PhraseDictionaryCompact name=TranslationModel0 num > > > > > > > -features=4 path=/pathtodata/binarised/phrase-table input > > > > > > > -factor=0 output-factor=0 > > > > > > > LexicalReordering name=LexicalReordering0 num-features=6 > > > > > > > type=wbe-msd-bidirectional-fe-allff input-factor=0 output > > > > > > > -factor=0 path=/pathtodata/binarised/reordering-table > > > > > > > Distortion > > > > > > > KENLM lazyken=0 name=LM0 factor=0 path=/pathtodata/blm.en > > > > > > > order=3 > > > > > > > > > > > > > > # dense weights for feature functions > > > > > > > [weight] > > > > > > > # The default weights are NOT optimized for translation > > > > > > > quality. You MUST tune the weights. > > > > > > > # Documentation for tuning is here: > > > > > > > http://www.statmt.org/moses/?n=FactoredTraining.Tuning > > > > > > > > > > > > > > Moses - FactoredTraining/Tuning www.statmt.org Tuning. > > > > > > > Overview. During decoding, Moses scores translation > > > > > > > hypotheses using a linear model. In the traditional > > > > > > > approach, the features of the model are the ... > > > > > > > UnknownWordPenalty0= 1 > > > > > > > WordPenalty0= -1 > > > > > > > PhrasePenalty0= 0.2 > > > > > > > TranslationModel0= 0.2 0.2 0.2 0.2 > > > > > > > LexicalReordering0= 0.3 0.3 0.3 0.3 0.3 0.3 > > > > > > > Distortion0= 0.3 > > > > > > > LM0= 0.5 > > > > > > > > > > > > > > /pathtomoses/mosesdecoder/scripts/training/mert-moses.pl > > > > > > > -no-filter-phrase-table true.fr true.en > > > > > > > /pathtomoses/mosesdecoder/bin/moses binarised/moses.ini - > > > > > > > -mertdir /pathtomoses/mosesdecoder/bin/ > > > > > > -- > > > > > > Hieu Hoang > > > > > > http://www.hoang.co.uk/hieu > > > > > -- > > > > > Hieu Hoang > > > > > http://www.hoang.co.uk/hieu > > > > > > > > -- > > > Hieu Hoang > > > http://www.hoang.co.uk/hieu > > > > > > _______________________________________________ > Moses-support mailing list > [email protected] > http://mailman.mit.edu/mailman/listinfo/moses-support -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. _______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
