> I am using GIZA++ to train my model. I have two questions regarding it: > > 1) How to set the Maximum sentence length? by default it is 100 but I have > sentences longer than that. How I can set it? Giza doesn't really support sentences longer than 100 words- you can change the limit in the code, but some of the models will underflow and very strange things will happen. Also, using very long sentences is extremely slow and the word alignments are usually quite poor.
> 2) How can I tell GIZA++ to train based on model 1, is there any parameter > file that I can set it? > > The command line I am using is as follows: > GIZA++ -S english.vcb -T foreign.vcb -C english_foreign.snt -O dic try -m1iterations N You might try looking at the command the moses's train-factored-phrase-model.perl invokes as a starting point. You can set -m1iterations to whatever you want and the other models to 0 iterations if you just want model 1. -Chris > > Thanks alot, > Andra > > _______________________________________________ > Moses-support mailing list > [email protected] > http://mailman.mit.edu/mailman/listinfo/moses-support > > _______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
