Moses-support Digest, Vol 89, Issue 35

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: Giza++ HMMTable readJumps implementation (Sara Stymne)
2. Re: Giza++ HMMTable readJumps implementation (Nicola Bertoldi)
3. Recaser - LM model loading (Tomas Fulajtar)
4. Re: phrase limit at bracket signs? (Philipp Koehn)


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

Message: 1
Date: Mon, 17 Mar 2014 11:06:00 +0100
From: Sara Stymne <sara.stymne@lingfil.uu.se>
Subject: Re: [Moses-support] Giza++ HMMTable readJumps implementation
To: <moses-support@mit.edu>
Message-ID: <5326C908.6080505@lingfil.uu.se>
Content-Type: text/plain; charset="iso-8859-1"

Hi,

You might want to have a look at mgiza, and this HOWTO on how to do
force alignment: http://www.kyloo.net/software/doku.php/mgiza:forcealignment

Best,
Sara


On 03/16/2014 05:49 PM, Nima Pourdamghani wrote:
> I need to load my probability tables into Giza++. Currently I am
> working with HMM model. I've managed to load the t-table, but loading
> the a-table (i.e. h-table) is not implemented in the version that I
> have (the body of readJumps function in HMMTables.cpp file is empty).
> Is there an implementation of this function available? If not how can
> one implement it?
>
> Cheers
>
>
> _______________________________________________
> 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/20140317/4a9705f0/attachment-0001.htm

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

Message: 2
Date: Mon, 17 Mar 2014 10:21:54 +0000
From: Nicola Bertoldi <bertoldi@fbk.eu>
Subject: Re: [Moses-support] Giza++ HMMTable readJumps implementation
To: Sara Stymne <sara.stymne@lingfil.uu.se>
Cc: moses-support support <moses-support@mit.edu>
Message-ID: <92D8144F-2659-497E-A93A-8938B99D39B3@fbk.eu>
Content-Type: text/plain; charset="us-ascii"

Hi Nima,

at FBK, we have recently develop a new (beta) version of MGIZA++ which enables online word alignment


Maybe you could use it directly or grasp the way we load the tables/models
do not hesitate to ask us any clarification.

You can find it here
http://hlt.fbk.eu/technologies/onlinemgiza


cheers,
Nicola




On Mar 17, 2014, at 11:06 AM, Sara Stymne wrote:

Hi,

You might want to have a look at mgiza, and this HOWTO on how to do force alignment: http://www.kyloo.net/software/doku.php/mgiza:forcealignment

Best,
Sara


On 03/16/2014 05:49 PM, Nima Pourdamghani wrote:
I need to load my probability tables into Giza++. Currently I am working with HMM model. I've managed to load the t-table, but loading the a-table (i.e. h-table) is not implemented in the version that I have (the body of readJumps function in HMMTables.cpp file is empty).
Is there an implementation of this function available? If not how can one implement it?

Cheers



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






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

Message: 3
Date: Mon, 17 Mar 2014 12:58:53 +0000
From: Tomas Fulajtar <TomasFu@moravia.com>
Subject: [Moses-support] Recaser - LM model loading
To: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID:
<0F546C639409F6479DF2CE6DD5267B16A040EA34@dag-cz-1.CZ.moravia-it.com>
Content-Type: text/plain; charset="us-ascii"

Hello,

I am experiencing strange behavior when using recaser LM model after migrated to moses(1.0) compiled on different machine.
The problem is that loading of LM takes 20 minutes on my new machine (SUSE), while on previous it was 20 secs or so.

Machine 1: Fedora 18:

* gcc: 4.7.2

* perl 5.16

* moses 1.0

* irstlm 5.80.01

* mgiza 0.7.0

* boost 1.52

Machine 2: SUSE SLES 11 SP3


* perl: 5.10.0

* gcc: 4.3

* moses 1.0

* irstlm 5.80.03

* mgiza 0.6.3

* boost 1.55

Moses compilation command:

sudo ./bjam --prefix=/opt/moses --install-scripts=/opt/moses/scripts -j4 -a --with-irstlm=/usr/local/irstlm --with-xmlrpc-c=/usr/local --with-cmph=usr/local --with-boost=/opt/boost --with-giza=/usr/local/bin --enable-boost-pool --enable-optimization --debug-symbols=off toolset=gcc -d2 --debug-configuration --max-kenlm-order=7 |tee ~/build.log 2>&1

I have tested the speed using the same recaser IRSTLM model data in ARPA format . There is actually no error displayed, thus I wonder where to continue with debugging. Also tried to retrain model on SUSE and then test on Fedora, but the result is same (no error, but too slow on SUSE). Does anybody have idea where to look for resolution? Maybe the problem is in IRSTLM used?


Thank you,

Tomas Fulajtar


-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20140317/ebad452b/attachment-0001.htm

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

Message: 4
Date: Mon, 17 Mar 2014 09:57:33 -0400
From: Philipp Koehn <pkoehn@inf.ed.ac.uk>
Subject: Re: [Moses-support] phrase limit at bracket signs?
To: Viktor Pless <viktor.pless@gmail.com>
Cc: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID:
<CAAFADDAS-znyAm2xmr0+DiRz-u5H-DVomRoy5irMKyds0QUNwg@mail.gmail.com>
Content-Type: text/plain; charset=ISO-8859-1

Hi,

another way to deal with brackets is to specify translations for them with
XML markup. The xml-exclusive option then overrides the translation \
table.
http://www.statmt.org/moses/?n=Moses.AdvancedFeatures#ntoc9

-phi

On Fri, Mar 14, 2014 at 4:23 AM, Viktor Pless <viktor.pless@gmail.com> wrote:
> Hi, is it possible to tell the algorithm which generates phrase pairs from
> the word aligments by growing them - to stop growing at brackets?
>
> It seems that brackets, wherever they turn up, confuse translation, perhaps
> because they are too numerous in the overall text and thus carry no
> information.
>
> thanks
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
>


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

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


End of Moses-support Digest, Vol 89, Issue 35
*********************************************

Tweet