Moses-support Digest, Vol 99, Issue 22

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. nplm Error (Marwa Refaie)
2. nplm Building LM (Marwa Refaie)
3. Re: Feature score deltas in the chart decoder (Jun-ya NORIMATSU)
4. Re: Start learning Moses (Mhmd Hasanen) (Hoai-Thu Vuong)


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

Message: 1
Date: Fri, 9 Jan 2015 00:39:45 +0000
From: Marwa Refaie <basmallah@hotmail.com>
Subject: [Moses-support] nplm Error
To: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID: <DUB118-W189DBD07A704D498B45C0BBA440@phx.gbl>
Content-Type: text/plain; charset="windows-1256"

I did fix all errors for Eigen & boost & TCLAp errors, then I run
make install
& Now I'm staking here !!!!marwa@MarwaVM:~/nplm-master/src$
make install

/usr/bin/g++ -c
-fopenmp -I/usr/share/boostbuild/include
-I/home/marwa/nplm-master/3rdparty/tclap/include -I/usr/include/eigen3 -O3
-DEIGEN_NO_DEBUG -DNDEBUG
trainNeuralNetwork.cpp -o trainNeuralNetwork.o

In file included
from trainNeuralNetwork.cpp:25:0:

/home/marwa/nplm-master/3rdparty/tclap/CmdLine.h:
In member function ?void TCLAP::CmdLine::_constructor()?:

/home/marwa/nplm-master/3rdparty/tclap/CmdLine.h:391:10:
error: expected type-specifier before ?IgnoreRestVisitor?

v = new IgnoreRestVisitor();

^

make: ***
[trainNeuralNetwork.o] Error 1
Any help please


Marwa N. Refaie


-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150109/48c78c50/attachment-0001.htm

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

Message: 2
Date: Mon, 12 Jan 2015 00:05:37 +0000
From: Marwa Refaie <basmallah@hotmail.com>
Subject: [Moses-support] nplm Building LM
To: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID: <DUB118-W17A8FB1B325244C18C7D48BA430@phx.gbl>
Content-Type: text/plain; charset="windows-1256"



HiPlease I need any step by step tutorial for the nplm .I compiled the package & make trainnueralnetworkLM , then I got the validation.ngrams & train.ngrams then I got 10 files , model.1 model.2 ........... model.10.I ran the ./bjam --with nplm .... Then what to do next now ??Please any help ??
Marwa N. Refaie


-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150112/62aeca4f/attachment-0001.htm

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

Message: 3
Date: Mon, 12 Jan 2015 13:49:31 +0900
From: Jun-ya NORIMATSU <info@jnory.com>
Subject: Re: [Moses-support] Feature score deltas in the chart decoder
To: moses-support@mit.edu
Message-ID: <54B3525B.1030907@jnory.com>
Content-Type: text/plain; charset=utf-8; format=flowed

Hi,

> In the Moses master branch I found one other feature function that
> requires modifications:
>
> moses/LM/DALMWrapper.cpp
>
> This feature is currently not covered by a regression test, and I don't
> have any setup with this feature myself. I would not be able to test any
> modifications in that code and therefore would like to request that the
> authors apply the necessary updates themselves.

I've just finished to check and update the code.
https://github.com/moses-smt/mosesdecoder/commit/39799188a0478eda822167202fb7d404b35fbaad
https://github.com/moses-smt/mosesdecoder/commit/832b725c595d586f8802be12588fce9b495d36b8

Please let me know if you find some problems.

By the way, I'd like to add the regression test in near future.
Would you mind my asking the place(directories or repositories...) to
add the test code?

Thanks,
--
Jun-ya NORIMATSU

> ??: [Moses-support] Feature score deltas in the chart decoder
> ??: 2015-01-08 04:17
> ???: Matthias Huck <mhuck@inf.ed.ac.uk>
> ??: Moses-support <moses-support@mit.edu>
>
> Hi,
>
> I've just pushed a commit to Moses that brings about a slight change
> wrt. the way the chart decoder deals with feature scores.
>
> The chart decoder now stores deltas of individual feature scores instead
> of constantly summing everything up. This behaviour is similar to what
> we have been doing in the phrase-based decoder since a long time
> already. The main purpose of this modification is to improve efficiency
> with sparse features a bit.
>
> https://github.com/moses-smt/mosesdecoder/commit/465b47566424efb707bdc063d0bff52b0650eb0a
>
>
>
> The modification may however break existing feature function
> implementations.
>
> As a rule of thumb, any feature function that calls
>
> ScoreComponentCollection::Assign()
> in
> EvaluateWhenApplied(const ChartHypothesis&, ...)
>
> is affected and needs to be adapted to the new behaviour.
>
> Basically, the ScoreComponentCollection variable passed to
> EvaluateWhenApplied() now accumulates the delta score of the current
> rule application only, whereas it was previously accumulating the
> overall score of the partial hypothesis.
> I.e., calling Assign() in EvaluateWhenApplied() now does not replace the
> overall score any more, but has the same effect as calling PlusEquals().
>
> If you are the author of a feature function that implements
> EvaluateWhenApplied(const ChartHypothesis&, ...) and calls Assign()
> within that method, or if you are using such a feature function in your
> experiments, please update your implementation. The feature function
> should call PlusEquals() instead and add a score delta.
>
> I've already updated moses/LM/Ken.cpp and moses/LM/Implementation.cpp
> and Rico has updated moses/LM/BilingualLM.cpp .
> In the Moses master branch I found one other feature function that
> requires modifications:
>
> moses/LM/DALMWrapper.cpp
>
> This feature is currently not covered by a regression test, and I don't
> have any setup with this feature myself. I would not be able to test any
> modifications in that code and therefore would like to request that the
> authors apply the necessary updates themselves.
>
> Please let me know in case you notice any issues or if you need any
> further information or advice regarding this modification.
>
> Cheers,
> Matthias


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

Message: 4
Date: Mon, 12 Jan 2015 08:01:34 +0000
From: Hoai-Thu Vuong <thuvh87@gmail.com>
Subject: Re: [Moses-support] Start learning Moses (Mhmd Hasanen)
To: moses-support@mit.edu, mhmd_hasnen@yahoo.com
Message-ID:
<CABBkmgrWAjP2rkRybDva0QApqb38uYzcsMLxpBGUtsnM-tofDw@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

Did you mean the translation mode, language model, etc???

You can follow an instruction (http://www.statmt.org/moses/?n=Moses.Baseline)
to build the baseline model.

Before building a translation system, there are two kind data, you have to
prepare:

+ Bilingual Data: some of a pair sentences in both language such as
(english - french)
+ Mono Data: some sentence in target language (which language you would to
translate into. If you would like to translate from english to french, the
target language is french).

On Mon Jan 12 2015 at 12:41:34 AM <moses-support-request@mit.edu> wrote:

> 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. Start learning Moses (Mhmd Hasanen)
> 2. Re: using LRscore instead of BLUE (Hieu Hoang)
> 3. Re: using LRscore instead of BLUE (Christophe Servan)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Sun, 11 Jan 2015 11:59:21 +0200
> From: Mhmd Hasanen <mhmd_hasnen@yahoo.com>
> Subject: [Moses-support] Start learning Moses
> To: moses-support List <moses-support@mit.edu>
> Message-ID: <103D51E6-EC1C-43BF-971E-F2B1F08CBF67@yahoo.com>
> Content-Type: text/plain; charset="us-ascii"
>
>
> > Hi all,
> > I need to start learning from txt or tax files how can I do that
> Thanks
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: http://mailman.mit.edu/mailman/private/moses-support/
> attachments/20150111/41219e1d/attachment-0001.htm
>
> ------------------------------
>
> Message: 2
> Date: Sun, 11 Jan 2015 14:03:29 +0000
> From: Hieu Hoang <Hieu.Hoang@ed.ac.uk>
> Subject: Re: [Moses-support] using LRscore instead of BLUE
> To: Arefeh Kazemi <arefeh_kazemi@yahoo.com>, Alexandra Birch
> <lexi.birch@gmail.com>
> Cc: Moses-support <moses-support@mit.edu>
> Message-ID:
> <CAEKMkbivm5eyJ3ZrPhzW+u3Ducts9Cjj6NeYZZy6=M63Ky3Vbg@
> mail.gmail.com>
> Content-Type: text/plain; charset="utf-8"
>
> The code that the previous thread was referring to is here
> https://github.com/moses-smt/mosesdecoder/tree/mert-mtm5
> I'm not sure if the LR Score is included in the code, and even if it is,
> you may need to update it to work with current version of Moses
>
> On 7 January 2015 at 14:14, Arefeh Kazemi <arefeh_kazemi@yahoo.com> wrote:
>
> > Hi
> >
> > I want to use mert with LRscore instead of blue (to tune a reordering
> > model). Is there any straightforward way to do that? Is it integrated
> into
> > moses or not?
> > I found this
> > <http://thread.gmane.org/gmane.comp.nlp.moses.user/6861/focus=6866>
> topic
> > in the archive but I couldn't find the code.
> >
> > Regards
> > Arefeh
> >
> > _______________________________________________
> > Moses-support mailing list
> > Moses-support@mit.edu
> > http://mailman.mit.edu/mailman/listinfo/moses-support
> >
> >
>
>
> --
> Hieu Hoang
> Research Associate
> University of Edinburgh
> http://www.hoang.co.uk/hieu
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: http://mailman.mit.edu/mailman/private/moses-support/
> attachments/20150111/16bbe7a4/attachment-0001.htm
>
> ------------------------------
>
> Message: 3
> Date: Sun, 11 Jan 2015 16:19:48 +0100
> From: Christophe Servan <christophe.servan@gmail.com>
> Subject: Re: [Moses-support] using LRscore instead of BLUE
> To: Hieu Hoang <Hieu.Hoang@ed.ac.uk>, Christophe Servan
> <christophe.servan@gmail.com>
> Cc: Moses-support <moses-support@mit.edu>, Arefeh Kazemi
> <arefeh_kazemi@yahoo.com>
> Message-ID:
> <CAAsGDkq62yDx69N0U7CxHELfout5wnKsRLSjWgGAD_81G40tMg@mail.
> gmail.com>
> Content-Type: text/plain; charset="utf-8"
>
> Hi,
> As far as I know the Permutation Scorer is implemented in the last version
> of moses (A. Birch & M. Osborne "LRscore for Evaluating Lexical and
> Reordering Quality in MT").
> You can use it by specifying "HAMMING" as scorer type like presented here
> http://www.statmt.org/moses/?n=FactoredTraining.Tuning
>
> Cheer,
>
> Christophe
>
>
> 2015-01-11 15:03 GMT+01:00 Hieu Hoang <Hieu.Hoang@ed.ac.uk>:
>
> > The code that the previous thread was referring to is here
> > https://github.com/moses-smt/mosesdecoder/tree/mert-mtm5
> > I'm not sure if the LR Score is included in the code, and even if it is,
> > you may need to update it to work with current version of Moses
> >
> > On 7 January 2015 at 14:14, Arefeh Kazemi <arefeh_kazemi@yahoo.com>
> wrote:
> >
> >> Hi
> >>
> >> I want to use mert with LRscore instead of blue (to tune a reordering
> >> model). Is there any straightforward way to do that? Is it integrated
> into
> >> moses or not?
> >> I found this
> >> <http://thread.gmane.org/gmane.comp.nlp.moses.user/6861/focus=6866>
> >> topic in the archive but I couldn't find the code.
> >>
> >> Regards
> >> Arefeh
> >>
> >> _______________________________________________
> >> Moses-support mailing list
> >> Moses-support@mit.edu
> >> http://mailman.mit.edu/mailman/listinfo/moses-support
> >>
> >>
> >
> >
> > --
> > Hieu Hoang
> > Research Associate
> > University of Edinburgh
> > http://www.hoang.co.uk/hieu
> >
> >
> > _______________________________________________
> > 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/20150111/dba3d262/attachment-0001.htm
>
> ------------------------------
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
>
> End of Moses-support Digest, Vol 99, Issue 21
> *********************************************
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150112/84a12b7a/attachment.htm

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

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


End of Moses-support Digest, Vol 99, Issue 22
*********************************************

Tweet