Moses-support Digest, Vol 113, Issue 49

Send Moses-support mailing list submissions to
moses-support@mit.edu

To subscribe or unsubscribe via the World Wide Web, visit
http://mailman.mit.edu/mailman/listinfo/moses-support
or, via email, send a message with subject or body 'help' to
moses-support-request@mit.edu

You can reach the person managing the list at
moses-support-owner@mit.edu

When replying, please edit your Subject line so it is more specific
than "Re: Contents of Moses-support digest..."


Today's Topics:

1. Re: BilingualNPLM: A target phrase with no alignments
detected! (Nikolay Bogoychev)
2. Re: BilingualNPLM: A target phrase with no alignments
detected! (Jeremy Gwinnup)
3. Re: problem while testing moses (Hieu Hoang)


----------------------------------------------------------------------

Message: 1
Date: Wed, 16 Mar 2016 16:21:43 +0000
From: Nikolay Bogoychev <nheart@gmail.com>
Subject: Re: [Moses-support] BilingualNPLM: A target phrase with no
alignments detected!
To: Jeremy Gwinnup <jeremy@gwinnup.org>
Cc: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID:
<CAJzPUEwPUPcAR9exvpo8XdvtyXAXwL=usNhfx8nRfhVhpNTZrg@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

Hey Jeremy,

The error you should get should be: "A target phrase with no alignments
detected! " << targetPhrase << "Check if there is something wrong with your
phrase table."); which should also include the targetPhrase in question.
My guess is that you use PhraseDictionaryCompact as your phrase table which
in some cases is known to produce target phrases without alignments. My
first suggestion would be check your phrase table and see if that target
phrase has alignments. If the target phrase has alignments then it is
probably lost during the the phrase table binarization. I would suggest
that you use a different phrase table or set EMS to use a single thread,
which should help avoid the problem.

Cheers,

Nick

On Wed, Mar 16, 2016 at 2:49 PM, Jeremy Gwinnup <jeremy@gwinnup.org> wrote:

> Hi,
>
> I?m attempting to use a BilingualNPLM (trained per the recipe on the moses
> website) in decoding - I get ?A target phrase with no alignments detected!?
> error. All data used in training the model were products of a training run
> in EMS. I?m using the recommended NPLM settings with the exception of
> setting the input embedding to 750.
>
> Any ideas as to if I need to train differently?
>
> Thanks!
> -Jeremy
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20160316/6171562f/attachment-0001.html

------------------------------

Message: 2
Date: Wed, 16 Mar 2016 13:27:59 -0400
From: Jeremy Gwinnup <jeremy@gwinnup.org>
Subject: Re: [Moses-support] BilingualNPLM: A target phrase with no
alignments detected!
To: Nikolay Bogoychev <nheart@gmail.com>
Cc: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID: <3A49EC07-B37F-4A3C-9BBD-ECD20BC76F26@gwinnup.org>
Content-Type: text/plain; charset="utf-8"

Nick,

That was the issue - I was using a ProbingPT. I switched back to PhraseDictionaryMemory and it?s now running fine.

Thanks!

> On Mar 16, 2016, at 12:21 PM, Nikolay Bogoychev <nheart@gmail.com> wrote:
>
> Hey Jeremy,
>
> The error you should get should be: "A target phrase with no alignments detected! " << targetPhrase << "Check if there is something wrong with your phrase table.");
> which should also include the targetPhrase in question. My guess is that you use PhraseDictionaryCompact as your phrase table which in some cases is known to produce target phrases without alignments. My first suggestion would be check your phrase table and see if that target phrase has alignments. If the target phrase has alignments then it is probably lost during the the phrase table binarization. I would suggest that you use a different phrase table or set EMS to use a single thread, which should help avoid the problem.
>
> Cheers,
>
> Nick
>
> On Wed, Mar 16, 2016 at 2:49 PM, Jeremy Gwinnup <jeremy@gwinnup.org <mailto:jeremy@gwinnup.org>> wrote:
> Hi,
>
> I?m attempting to use a BilingualNPLM (trained per the recipe on the moses website) in decoding - I get ?A target phrase with no alignments detected!? error. All data used in training the model were products of a training run in EMS. I?m using the recommended NPLM settings with the exception of setting the input embedding to 750.
>
> Any ideas as to if I need to train differently?
>
> Thanks!
> -Jeremy
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu <mailto:Moses-support@mit.edu>
> http://mailman.mit.edu/mailman/listinfo/moses-support <http://mailman.mit.edu/mailman/listinfo/moses-support>
>

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20160316/83e4e20b/attachment-0001.html

------------------------------

Message: 3
Date: Wed, 16 Mar 2016 22:10:52 +0000
From: Hieu Hoang <hieuhoang@gmail.com>
Subject: Re: [Moses-support] problem while testing moses
To: sofiane bouzaher <bouzaher.sofiane@gmail.com>, moses-support
<moses-support@mit.edu>
Message-ID: <56E9D9EC.5020008@gmail.com>
Content-Type: text/plain; charset="utf-8"

--with-cmph=/home/hieu/workspace/cmph-2.0
not
--with-cmph=~/home/hieu/workspace/cmph-2.0

On 16/03/2016 20:39, sofiane bouzaher wrote:
> Hi, sorry
> here is the command we use to compile moses
> ./bjam --with-boost=/home/hieu/workspace/boost_1_57_0
> --with-cmph=~/home/hieu/workspace/cmph-2.0 -j8
>
> 2016-03-11 3:02 GMT+01:00 Hieu Hoang <hieuhoang@gmail.com
> <mailto:hieuhoang@gmail.com>>:
>
> What was the exact command you used to compile moses? ie. ./bjam ....
>
> It doesn't look like the cmph library was linked to moses so the
> compact phrase-table wasn't compiled.
>
>
> On 10/03/2016 21:33, sofiane bouzaher wrote:
>
> Hi,we are trying use the moses toolkit for a Rapid
> Construction of Supervised Word Sense Disambiguation System
> for Lesser-resourced Languages (arabic) we use the virtual
> machine (ubuntu 14.04 32-bit.ova 30-Jan-2015 16:41 7.2G), we
> we have compiled moses withs cmph2.0 and boost_ 1_57_0 as
> recommanded alla steps passed succufully, but when we try to
> run Moses with compact phrase table using
> "/home/hieu/workspace/github/mosesdecoder/bin/moses -f
> /home/hieu/working/binarised-model/moses.ini" we get this error
>
> hieu@hieu-VirtualBox:~$
> /home/hieu/workspace/github/mosesdecoder/bin/moses -f
> /home/hieu/working/binarised-model/moses.ini
> Defined parameters (per moses.ini or switch):
> config: /home/hieu/working/binarised-model/moses.ini
> distortion-limit: 6
> feature: UnknownWordPenalty WordPenalty PhrasePenalty
> PhraseDictionaryCompact name=TranslationModel0 num-features=4
> path=/home/hieu/working/binarised-model/phrase-table.minphr
> input-factor=0 output-factor=0 LexicalReordering
> name=LexicalReordering0 num-features=6
> type=wbe-msd-bidirectional-fe-allff input-factor=0
> output-factor=0
> path=/home/hieu/working/binarised-model/reordering-table.minlexr
> Distortion KENLM lazyken=0 name=LM0 factor=0
> path=/home/hieu/lm/news-commentary-v8.fr-en.blm.en order=3
> input-factors: 0
> mapping: 0 T 0
> weight: UnknownWordPenalty0= 1 WordPenalty0= -1
> PhrasePenalty0= 0.2 TranslationModel0= 0.2 0.2 0.2 0.2
> LexicalReordering0= 0.3 0.3 0.3 0.3 0.3 0.3 Distortion0= 0.3
> LM0= 0.5
> line=UnknownWordPenalty
> FeatureFunction: UnknownWordPenalty0 start: 0 end: 0
> line=WordPenalty
> FeatureFunction: WordPenalty0 start: 1 end: 1
> line=PhrasePenalty
> FeatureFunction: PhrasePenalty0 start: 2 end: 2
> line=PhraseDictionaryCompact name=TranslationModel0
> num-features=4
> path=/home/hieu/working/binarised-model/phrase-table.minphr
> input-factor=0 output-factor=0
> Exception: moses/FF/Factory.cpp:321 in void
> Moses::FeatureRegistry::Construct(const string&, const
> string&) threw UnknownFeatureException because `i ==
> registry_.end()'.
> Feature name PhraseDictionaryCompact is not registered.
>
>
> we need help please ,
> and also an idea for the possibility to use of arabic language ?
>
> the moses.ini file :
> #########################
> ### MOSES CONFIG FILE ###
> #########################
>
> # input factors
> [input-factors]
> 0
>
> # mapping steps
> [mapping]
> 0 T 0
>
> [distortion-limit]
> 6
>
> # feature functions
> [feature]
> UnknownWordPenalty
> WordPenalty
> PhrasePenalty
> PhraseDictionaryCompact name=TranslationModel0 num-features=4
> path=/home/hieu/working/binarised-model/phrase-table.minphr
> input-factor=0 output-factor=0
> LexicalReordering name=LexicalReordering0 num-features=6
> type=wbe-msd-bidirectional-fe-allff input-factor=0
> output-factor=0
> path=/home/hieu/working/binarised-model/reordering-table.minlexr
> Distortion
> KENLM lazyken=0 name=LM0 factor=0
> path=/home/hieu/lm/news-commentary-v8.fr-en.blm.en order=3
>
> # dense weights for feature functions
> [weight]
> UnknownWordPenalty0= 1
> WordPenalty0= -1
> PhrasePenalty0= 0.2
> TranslationModel0= 0.2 0.2 0.2 0.2
> LexicalReordering0= 0.3 0.3 0.3 0.3 0.3 0.3
> Distortion0= 0.3
> LM0= 0.5
>
>
>

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20160316/cefa0ce7/attachment.html

------------------------------

_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support


End of Moses-support Digest, Vol 113, Issue 49
**********************************************

Tweet