Hi, 4 minutes sounds like too much for translating a sentence. A little bit more detail would be helpful to detect where the time savings could be: - does the time include the start-up time (loading translation and language models)? - do you use IRSTLM, SRILM, binarized phrase and reordering tables?
There are many ways for speeding things up (using / not using binarized data structures, beam settings, translation table limits, filtering and pruning). -phi 2009/5/5 <[email protected]>: >>actually, i think Jan wants a speedup, not a space saving. >> >>your best bet is to reduce the size of the beam: >> >>http://www.statmt.org/moses/?n=Moses.Tutorial#ntoc6 > > Yes, I want to speedup translating (decoding), and it can be connected with > decreasing quality of results. > > I tried to reduce the size of beam as in example on webpage, but I can't see > that anything changed. Can anyone > give an example of reducing beam command ? > > Mayby another way to speedup is to change some parameters connected with > building a langugage model. Any ideas? > > Please, help. > > > Regards, > Jan Helak > UAM University, Poland > > > _______________________________________________ > 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
