Moses-support Digest, Vol 113, Issue 21

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: RNNLM Integration? (Matthias Huck)
2. Moses build problems (Shani Shalgi)
3. Re: Moses build problems (Jeroen Vermeulen)


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

Message: 1
Date: Tue, 08 Mar 2016 17:19:13 +0000
From: Matthias Huck <mhuck@inf.ed.ac.uk>
Subject: Re: [Moses-support] RNNLM Integration?
To: Lane Schwartz <dowobeha@gmail.com>
Cc: "moses-support@mit.edu" <moses-support@mit.edu>, Philipp Koehn
<phi@jhu.edu>
Message-ID: <1457457553.3234.186.camel@portedgar>
Content-Type: text/plain; charset="UTF-8"

Hi,

We once empirically compared two different recombination schemes in a
hierarchical phrase-based system (without any kind of neural network
language model):

Recombination T. The T recombination scheme recombines derivations that
produce identical translations. (I.e., hypotheses with the same
translation but different phrase segmentation are recombined.)

Recombination LM. The LM recombination scheme recombines derivations
with identical language model context. (This is what we'd usually do.)


Cf. the following publication:

M. Huck, D. Vilar, M. Freitag, and H. Ney. A Performance Study of Cube
Pruning for Large-Scale Hierarchical Machine Translation. In Proceedings
of the NAACL 7th Workshop on Syntax, Semantics and Structure in
Statistical Translation (SSST-7), pages 29-38, Atlanta, Georgia, USA,
June 2013.
http://aclweb.org/anthology//W/W13/W13-0804.pdf


You'll find a couple of statistics and performance plots in the paper
for Chinese-to-English and Arabic-to-English translation tasks. This was
all done with the Jane SMT toolkit.
http://www.hltpr.rwth-aachen.de/jane/
Note that the cube pruning k-best generation limit was applied after
recombination for the experiments in the paper.


I tend to think that you could do the "Recombination T" scheme if the
benefit of an RNNLM in terms of translation quality justifies it. There
might be pitfalls, e.g. regarding pruning settings and tuning on n-best
lists. Default Moses settings won't necessarily be a good choice.

Cheers,
Matthias


On Mon, 2016-03-07 at 15:41 -0600, Lane Schwartz wrote:
> Philipp,
>
> Are you aware of any published work examining the importance of hypothesis
> recombination in terms of time/space/quality tradeoffs?
>
> Lane
>
>
> On Mon, Mar 7, 2016 at 3:19 PM, Philipp Koehn <phi@jhu.edu> wrote:
>
> > Hi,
> >
> > integrating this into the decoder will break all hypothesis recombination,
> > so it may be better (and definitely easier) to use the RNNLM to rerank
> > n-best lists.
> >
> > -phi
> >
> > On Mon, Mar 7, 2016 at 3:46 PM, Jake Ballinger <ballingerj@allegheny.edu>
> > wrote:
> >
> >> Hello everyone,
> >>
> >> Has anyone used an RNNLM language model instead of one of the recommended
> >> language models? I was specifically looking at the RNNLM toolkit provided
> >> by Tomas Mikolov at http://rnnlm.org/.
> >>
> >> Thank you!
> >>
> >> --
> >> Jake Ballinger
> >> Major: Computer Science
> >> Minors: Chinese, French, Spanish, & Math
> >> 443-974-6184
> >> ballingerj@allegheny.edu
> >> Box 582
> >>
> >> _______________________________________________
> >> 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
> >
> >
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support



--
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.



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

Message: 2
Date: Wed, 9 Mar 2016 12:39:01 +0200
From: Shani Shalgi <shanishalgi@gmail.com>
Subject: [Moses-support] Moses build problems
To: moses-support@mit.edu
Message-ID:
<CAJ5=UKR9hi4orHP_tsea-dtGHKs9bwnw8ehrvgskpCAJ8QMXLA@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

I've successfully compiled moses before, and successfuly run it many times
including yesterday.
However, today I wanted to recompile with a new feature - xmlrcp.
The compile failed and now I can't compile even with a simple ./bjam -j8.
Please help me, I've searched the forums and google and done everything
suggested.
Attached is my log file.
TIA, Shani
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20160309/f21297cb/attachment-0001.html
-------------- next part --------------
A non-text attachment was scrubbed...
Name: build.log.gz
Type: application/x-gzip
Size: 11887 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20160309/f21297cb/attachment-0001.gz

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

Message: 3
Date: Wed, 9 Mar 2016 13:12:50 +0100
From: Jeroen Vermeulen <jtv@precisiontranslationtools.com>
Subject: Re: [Moses-support] Moses build problems
To: Shani Shalgi <shanishalgi@gmail.com>, moses-support@mit.edu
Message-ID: <56E01342.2000808@precisiontranslationtools.com>
Content-Type: text/plain; charset=windows-1252

On 2016-03-09 11:39, Shani Shalgi wrote:
> I've successfully compiled moses before, and successfuly run it many
> times including yesterday.
> However, today I wanted to recompile with a new feature - xmlrcp.
> The compile failed and now I can't compile even with a simple ./bjam -j8.
> Please help me, I've searched the forums and google and done everything
> suggested.

That log shows a successful build, doesn't it?


Jeroen



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

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


End of Moses-support Digest, Vol 113, Issue 21
**********************************************

Tweet