Once you create the alignment file from Berkeley, you pick-up train-model.perl training at step 4. So, add the --do-steps=4-9 argument to your command line. You might also want to use the --alignment-file or --alignment-stem arguments to point directly to your Berlekey alignment file.
On 12/18/2015 12:01 AM, [email protected] wrote: > Date: Wed, 16 Dec 2015 22:37:11 +0900 > From: Andrew<[email protected]> > Subject: [Moses-support] how to train with berkeley word aligner > To:"[email protected]" <[email protected]> > Message-ID:<[email protected]> > Content-Type: text/plain; charset="iso-2022-jp" > > I'm replicating the steps described in Baseline System page,and am about to > run the following command,except I want to run it with pre-compiled berkeley > word aligner rather than mgiza or giza++ (since their installations have been > troublesome)Should I fix the command below or code in somewhere?In any case, > how should it be fixed? > > mkdir ~/working > cd ~/working > nohup nice ~/mosesdecoder/scripts/training/train-model.perl -root-dir train > \ > -corpus ~/corpus/news-commentary-v8.fr-en.clean > \ > -f fr -e en -alignment grow-diag-final-and -reordering msd-bidirectional-fe > \ > -lm 0:3:$HOME/lm/news-commentary-v8.fr-en.blm.en:8 > \ > -external-bin-dir ~/mosesdecoder/tools >& training.out & > _______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
