Yes, that's correct. At minimum, you want to train the language model on the target language half of your parallel corpus, but you can also add data from other non-parallel sources to improve performance. For an extreme example see: http://aclweb.org/anthology-new/D/D07/D07-1090.pdf
Cheers Adam On 17 Jul 2008, at 08:53, Vineet Kashyap wrote: > Hi all > > Can someone please clarify that the language model > is trained on the target language whereas the translation > model is trained on the bi-lingual corpus ? > > Thanks > > Vineet > > _______________________________________________ > Moses-support mailing list > [email protected] > http://mailman.mit.edu/mailman/listinfo/moses-support -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. _______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
