[Moses-support] MT Marathon 2016 in Prague: Second Call for Papers, Projects and Participation

(Apologies for multiple copies.) = MT Marathon 2016, September 12-17, Prague = * The registration for MT Marathon 2016 in Prague is open. * Keynote speakers are invited. * The programme of lectures and labs will have a pronounced focus on Neural MT. (Tentative version of the programme

Re: [Moses-support] telling the training script where GIZA++ was installed

Hello. Could some one help me on the above issue please. I just donot know how I could specify corpus as to the above error. Thanks On 14 Jul 2016 1:23 pm, "Irene Nandutu" wrote: > Hello moses team, > Am using the baseline and > have successfull

[Moses-support] MOSES for segmentation

Hello moses team, We know that Moses use a beam search algorithm to find the best translation for a given source sentence. What I want to know, is if there is a beam search algorithm (or another) to find the best segmentation for given source and target sentence (source and translation)

Re: [Moses-support] help regarding languages used for translation

I can't vouch for it. I just remember being surprised someone contributed the file a while ago. It but it seems to be a simple starting point since it's there. Tom On 7/14/2016 6:26 PM, Anoop (അനൂപ്) wrote: Thanks Tom, I didn't know there was one in Moses for Tamil! Regards Anoop. On Thu,

Re: [Moses-support] Moses-support Digest, Vol 117, Issue 23

Thanks Tom, I didn't know there was one in Moses for Tamil! Regards Anoop. On Thu, Jul 14, 2016 at 4:17 PM, Tom Hoar wrote: > Re "Moses does not have tokenizers for Tamil", actually there is a Tamil > nonbreaking prefix file in the folder > scripts/share/nonbreaking_prefixes/nonbreaking_prefix.

[Moses-support] Fwd: Moses-support post from ameur.do...@inria.fr requires approval

Please subscribe to the Moses mailing list before posting to it. You can subscribe here: http://mailman.mit.edu/mailman/listinfo/moses-support To answer your question - Moses can do constrained decoding: http://www.statmt.org/moses/?n=Advanced.Constrained Hieu Hoang http://www.hoang.co.uk/h

Re: [Moses-support] Moses-support Digest, Vol 117, Issue 23

Re "Moses does not have tokenizers for Tamil", actually there is a Tamil nonbreaking prefix file in the folder scripts/share/nonbreaking_prefixes/nonbreaking_prefix.ta. You might want to start simple starting with the scripts/tokenizer/tokenizer.perl file. Then after you see how it works, escal

[Moses-support] telling the training script where GIZA++ was installed

Hello moses team, Am using the baseline and have successfully achieved the earlier steps and all is okay. But now non the step of training the translation system. I first wrote the command of telling the training script where GIZA++ was installed and

Re: [Moses-support] Moses Installation

This worked Thanks Irene Nandutu +256781595675 Twitter Google+ On Tue, Jul 5, 2016 at 1:25 PM, Tom Hoar wrote: > Irene, > > It looks like you need a primer course in how to work with the terminal, >

Re: [Moses-support] help regarding languages used for translation

Hi Selva, Moses is language-independent, so you can use it for any language pair as long as you have a parallel corpus. That said, you may have to do language specific pre and post-processing. For instance, - Moses does not have tokenizers for Tamil. - Tamil is agglutinative, so you may want to s