Moses-support Digest, Vol 100, Issue 78

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. errors in LM and tuning steps (fatma elzahraa Eltaher)
2. Re: errors in LM and tuning steps (Philipp Koehn)
3. Fill-up for reordering models (Marcin Junczys-Dowmunt)
4. Re: Fill-up for reordering models (Christophe Servan)
5. Re: missing .gz files at the end of mgiza (Vito Mandorino)


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

Message: 1
Date: Mon, 23 Feb 2015 10:07:42 -0800
From: fatma elzahraa Eltaher <fatmaeltaher@gmail.com>
Subject: [Moses-support] errors in LM and tuning steps
To: moses-support@mit.edu
Message-ID:
<CAOW1BbRbeFdB1gBLuyy7JiEbxJecZM0E5Ej-KuxJ+V1Pb9fRDw@mail.gmail.com>
Content-Type: text/plain; charset="iso-8859-1"

Dears,

I get errors in Lm and tuning steps . but I could not solve them so I
attached the stderr files of them.
please help me with some advices


thank you,



Fatma El-Zahraa El -Taher

Teaching Assistant at Computer & System department

Faculty of Engineering, Azhar University

Email : fatmaeltaher@gmail.com
mobile: +201141600434
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150223/c1941228/attachment-0001.htm
-------------- next part --------------
A non-text attachment was scrubbed...
Name: LM_toy_train.58.STDERR
Type: application/octet-stream
Size: 878 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20150223/c1941228/attachment-0003.obj
-------------- next part --------------
A non-text attachment was scrubbed...
Name: TUNING_input-from-sgm.58.STDERR
Type: application/octet-stream
Size: 241 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20150223/c1941228/attachment-0004.obj
-------------- next part --------------
A non-text attachment was scrubbed...
Name: TUNING_reference-from-sgm.58.STDERR
Type: application/octet-stream
Size: 327 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20150223/c1941228/attachment-0005.obj

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

Message: 2
Date: Mon, 23 Feb 2015 14:54:18 -0500
From: Philipp Koehn <phi@jhu.edu>
Subject: Re: [Moses-support] errors in LM and tuning steps
To: fatma elzahraa Eltaher <fatmaeltaher@gmail.com>
Cc: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID:
<CAAFADDDdCFjExUBk_SQ9NaroSR7bAMFjqysKX7uhT8W7gpdYRQ@mail.gmail.com>
Content-Type: text/plain; charset=UTF-8

Hi,

the errors in the SGM steps stem from errors in your config file.

The input-sgm file specification seems to include "<" or ">",
and the reference-sgm includes space characters. I am guessing
here, but please check how the command in the step file is
rendered.

-phi


On Mon, Feb 23, 2015 at 1:07 PM, fatma elzahraa Eltaher
<fatmaeltaher@gmail.com> wrote:
> Dears,
>
> I get errors in Lm and tuning steps . but I could not solve them so I
> attached the stderr files of them.
> please help me with some advices
>
>
> thank you,
>
>
>
> Fatma El-Zahraa El -Taher
>
> Teaching Assistant at Computer & System department
>
> Faculty of Engineering, Azhar University
>
> Email : fatmaeltaher@gmail.com
> mobile: +201141600434
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
>


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

Message: 3
Date: Mon, 23 Feb 2015 23:45:47 +0100
From: Marcin Junczys-Dowmunt <junczys@amu.edu.pl>
Subject: [Moses-support] Fill-up for reordering models
To: moses-support <moses-support@mit.edu>
Message-ID: <54EBAD9B.4010704@amu.edu.pl>
Content-Type: text/plain; charset=utf-8; format=flowed

Hi List,
in the domain adaptation section on the Moses website (BTW nice work!),
it says that fill-up can also be used for reordering models. Does the
additional binary feature just work (after setting it correctly in the
ini file)?
Thanks,
Best,
Marcin


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

Message: 4
Date: Tue, 24 Feb 2015 10:03:44 +0100
From: Christophe Servan <christophe.servan@gmail.com>
Subject: Re: [Moses-support] Fill-up for reordering models
To: Marcin Junczys-Dowmunt <junczys@amu.edu.pl>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CAAsGDkpVdoEN9ak5Avy_ifi1rVpJp0fwv=9Xzp9aJ4gkuaywCQ@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

Hello Marcin,
As far as I've tested, it works but the improvement is not very impressive
:)
I applied just the padding on the reordering model (like the fill-up but
without the binary feature) and it worked nearly as good as the fill-up
approach.

Cheers,

Christophe


2015-02-23 23:45 GMT+01:00 Marcin Junczys-Dowmunt <junczys@amu.edu.pl>:

> Hi List,
> in the domain adaptation section on the Moses website (BTW nice work!),
> it says that fill-up can also be used for reordering models. Does the
> additional binary feature just work (after setting it correctly in the
> ini file)?
> Thanks,
> Best,
> Marcin
> _______________________________________________
> 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/20150224/1fd6774a/attachment-0001.htm

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

Message: 5
Date: Tue, 24 Feb 2015 10:35:54 +0100
From: Vito Mandorino <vito.mandorino@linguacustodia.com>
Subject: Re: [Moses-support] missing .gz files at the end of mgiza
To: Tom Hoar <tahoar@precisiontranslationtools.com>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CA+8mSmHsQPYiQL8F-dKBJXMecuyW1bOinDBfApOanXZK05op+g@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

Thank you, I did have indeed a bad ratio in a previous try but not in this
one. I have launched the clean-corpus.perl script right before the
training.
In the log output there are actually several lines with warnings such as:

PROBLEM: alignment is 0.
WARNING: Hill Climbing yielded a zero score viterbi alignment for the
following pair:
WARNING: Model2 viterbi alignment has zero score.
Fert[50] selected WARNING: Model2 viterbi alignment has zero score.
WARNING: already 41 iterations in hillclimb: 3.24683 2 26 29
WARNING: DIFFERENT SUMS: (1) (3.13379)

Vito


2015-02-20 19:18 GMT+01:00 Tom Hoar <tahoar@precisiontranslationtools.com>:

> Fatal errors during step 2 are normally traceable to poor corpus
> preparation. Termination, however, does not always happen immediately. Look
> through the entire log output. You'll probably find one of these errors:
>
> "WARNING: The following sentence pair has source/target sentence length
> ration more than"
>
> or "ERROR: Forbidden zero sentence length 0"
>
> or a line beginning with "ERROR:"
>
> The fact that your corpus has placeholders makes me suspect you probably
> have a bad ratio.
>
>
>
>
>
> On 02/20/2015 06:18 PM, Vito Mandorino wrote:
>
> Dear All,
>
> I am training a model with placeholders from French to English and the
> process ends before the end of training step 2, without creating the
> en-fr.AR.final.gz and fr-en.AR.final.gz files in the respective
> folders giza.en-fr and giza.fr-en .
>
> I cannot understand why. Here's the last 7 lines of the training.out
> file:
>
>
> Entire Viterbi H333444 Training took: 78424 seconds
> ==========================================================
>
> Entire Training took: 134751 seconds
> Program Finished at: Fri Feb 20 05:45:19 2015
>
> ==========================================================
>
>
> and here's the command used for training:
>
> nohup nice /home/Moses/mosesdecoder/scripts/training/train-model.perl \
> --parallel \
> -mgiza -mgiza-cpus 20 \
> -root-dir /home/BRIQUES/train-leclerc-light-ph-fren/training \
> -external-bin-dir /root/external-bin-dir/ \
> -corpus
> /home/BRIQUES/train-leclerc-light-ph-enfr/data/Corpus.leclerc-ph.cleanclean
> -f fr -e en \
> -alignment grow-diag-final-and -reordering msd-bidirectional-fe \
> -lm 0:5:/home/DATA/LM/RapAnSoc/lm.RapAnSoc5-ph.blm.en.mm:8 \
> -write-lexical-counts \
> -extract-options '--Placeholders @num@,@rom@,@alpha@' \
> >& /home/BRIQUES/train-leclerc-light-ph-fren/training/training.out &
>
>
> It seems a bit odd to me that the analogous training in the reversed
> English-French direction has worked nicely.
> In fact, in this case the folders giza.en-fr and giza.fr-en do contain not
> only the .gz files but also two more "chunks" en-fr.A3.final.partD and
> en-fr.A3.final.partE, whereas the French-English training stops at
> fr-en.A3.final.partC.
>
>
> Thank you,
>
> Vito Mandorino
>
> --
>
>
> [image: Description : Description : lingua_custodia_final full logo]
>
> *The Translation Trustee*
>
> *1, Place Charles de Gaulle, **78180 Montigny-le-Bretonneux*
>
> *Tel : +33 1 30 44 04 23 Mobile : +33 6 84 65 68 89
> <%2B33%206%2084%2065%2068%2089>*
>
> *Email :* *vito.mandorino@linguacustodia.com
> <massinissa.ahmim@linguacustodia.com>*
>
> *Website :* *www.linguacustodia.com <http://www.linguacustodia.com/> -
> www.thetranslationtrustee.com <http://www.thetranslationtrustee.com/>*
>
>
> _______________________________________________
> Moses-support mailing listMoses-support@mit.eduhttp://mailman.mit.edu/mailman/listinfo/moses-support
>
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
>


--
*M**. Vito MANDORINO -- Chief Scientist*


[image: Description : Description : lingua_custodia_final full logo]

*The Translation Trustee*

*1, Place Charles de Gaulle, **78180 Montigny-le-Bretonneux*

*Tel : +33 1 30 44 04 23 Mobile : +33 6 84 65 68 89*

*Email :* *vito.mandorino@linguacustodia.com
<massinissa.ahmim@linguacustodia.com>*

*Website :* *www.linguacustodia.com <http://www.linguacustodia.com/> -
www.thetranslationtrustee.com <http://www.thetranslationtrustee.com/>*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150224/a839abca/attachment.htm
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.jpg
Type: image/jpeg
Size: 4421 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20150224/a839abca/attachment.jpg
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: image/jpeg
Size: 4421 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20150224/a839abca/attachment-0001.jpg

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

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


End of Moses-support Digest, Vol 100, Issue 78
**********************************************

0 Response to "Moses-support Digest, Vol 100, Issue 78"

Post a Comment