Hi, I am not sure what you mean by "VS.2005", but if you check out the latest version of Moses from github, and use * kenlm with binaries language model * binarize the phrase translation table (possibly after filtering) then loading time should be reduced to fractions of a second.
-phi On Sun, Aug 26, 2012 at 5:07 AM, saeed farzi <[email protected]> wrote: > Dear all, > I am using Moses (VS.2005) with a large phrase table and a language > model, but it takes very long time for loading them in to the memory. > I am looking for a solution to decrease the loading time. I think , a > binary version of phrase table and lm may be a solution, but i do not > know if Moses on VS.2005 can use th binary version of training data? > also would you plz tell me how i can use KenLM ? > i run moses with a binary version of training data in linux. but i > did do it in windows > > tnx in advance, > -- > S.Farzi, Ph.D. Student > Natural Language Processing Lab, > School of Electrical and Computer Eng., > Tehran University > Tel: +9821-6111-9719 > _______________________________________________ > 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
