Hi,

just use the switches "first-step" and "last-step".

-phi

2010/8/24 Wenlong Yang <[email protected]>:
> Hi all,
>
> From the training manual, we can see that, there are totally 9 steps for a
> new engine's training:
> Steps: (--first-step to --last-step)
> (1) prepare corpus
> (2) run GIZA
> (3) align words
> (4) learn lexical translation
> (5) extract phrases
> (6) score phrases
> (7) learn reordering model
> (8) learn generation model
> (9) create decoder config file
>
> And above steps are all performed by one script/command line:
> train-factored-phrase-model.perl
>
> Now I am training a very large corpus, and because of memory and disk
> limations, this command line always failed somewhere, so is there any way
> for us to just run several above steps to proceed our last failed training?
> If so, how to run the command line to do so?
>
> Thanks so,
> Wenlong
>
>
> _______________________________________________
> 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

Reply via email to