Moses-support Digest, Vol 91, Issue 42

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. Fwd: Using xml markup in EMS (Wei Qiu)
2. Re: Using xml markup in EMS (Wei Qiu)
3. n-grams in source language (Andrew)
4. MT Marathon 2014 Call for Papers and Participation (marco turchi)


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

Message: 1
Date: Mon, 26 May 2014 11:26:24 +0200
From: Wei Qiu <wei@qiu.es>
Subject: [Moses-support] Fwd: Using xml markup in EMS
To: moses-support <moses-support@mit.edu>
Message-ID:
<CALWr_T-duZT58Ar9d-6S=CQ_WheMCK=yEFyqeF+kT9Le7A7E-g@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

---------- Forwarded message ----------
From: Wei Qiu <wei@qiu.es>
Date: Mon, May 26, 2014 at 11:25 AM
Subject: Re: [Moses-support] Using xml markup in EMS
To: Philipp Koehn <pkoehn@inf.ed.ac.uk>


http://www.statmt.org/moses/?n=Moses.AdvancedFeatures#ntoc11
Yes, that's exactly what I mean.

Thanks.

Best,
Wei


On Mon, May 26, 2014 at 6:57 AM, Philipp Koehn <pkoehn@inf.ed.ac.uk> wrote:

> Hi,
>
> this is indeed not properly supported.
>
> I would suggest to tokenize the input for tuning and testing outside
> EMS and specify the tokenized files.
>
> Just to be clear:
> Are you talking about XML instructions to Moses as described here:
> http://www.statmt.org/moses/?n=Moses.AdvancedFeatures#ntoc11
>
> Or are you talking about tags that happen to be in your input and that
> should be preserved? In that case it is probably better to strip out
> the tags and re-insert them afterwards into the output with the help
> of word alignment.
>
> -phi
>
>
> On Sun, May 25, 2014 at 12:16 AM, Wei Qiu <wei@qiu.es> wrote:
> > Hi,
> >
> > Is it also reasonable to use xml markup for tuning?
> >
> > How can I use xml markup in ems? I am asking because it seems that the
> > tokenize step would break the xml tags into tokens.
> >
> > Thanks in advance.
> >
> > Best,
> > Wei
> >
> > _______________________________________________
> > 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/20140526/426d617e/attachment-0001.htm

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

Message: 2
Date: Mon, 26 May 2014 11:27:07 +0200
From: Wei Qiu <wei@qiu.es>
Subject: Re: [Moses-support] Using xml markup in EMS
To: Barry Haddow <bhaddow@staffmail.ed.ac.uk>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CALWr_T-Asp24uy4xzimDKObmhwCCq2H+TvRyQQHm2Qm1aqutCw@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

Thanks for the information.

Best,
Wei


On Mon, May 26, 2014 at 10:21 AM, Barry Haddow
<bhaddow@staffmail.ed.ac.uk>wrote:

> Hi Wei
>
> You can "protect" certain patterns from the tokeniser using the -protected
> <FILENAME> switch. The filename should contain regular expressions which
> signal which terms you want to protect. This could be used to prevent the
> tokeniser from breaking up xml tags - I have used it for URLs.
>
> cheers - Barry
>
>
> On 24/05/14 18:16, Wei Qiu wrote:
>
> Hi,
>
> Is it also reasonable to use xml markup for tuning?
>
> How can I use xml markup in ems? I am asking because it seems that the
> tokenize step would break the xml tags into tokens.
>
> Thanks in advance.
>
> Best,
> Wei
>
>
> _______________________________________________
> Moses-support mailing listMoses-support@mit.eduhttp://mailman.mit.edu/mailman/listinfo/moses-support
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20140526/498d8d76/attachment-0001.htm

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

Message: 3
Date: Mon, 26 May 2014 19:16:12 +0900
From: Andrew <ravenyj@hotmail.com>
Subject: [Moses-support] n-grams in source language
To: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID: <BAY181-W34C0626DA05E44D039AB25B23B0@phx.gbl>
Content-Type: text/plain; charset="iso-2022-jp"

Hello,
I know that language model is constructed using n-gram from target language,but where does the process that compares the n-grams used in source language to n-grams used in target language take place? i.e. In what stage?
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20140526/61f26b15/attachment-0001.htm

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

Message: 4
Date: Mon, 26 May 2014 17:19:27 +0200
From: marco turchi <marco.turchi@gmail.com>
Subject: [Moses-support] MT Marathon 2014 Call for Papers and
Participation
To: moses-support <moses-support@mit.edu>
Cc: linguist@listserv.linguistlist.org, corpora@uib.no,
elsnet-list@elsnet.org, dbworld@cs.wisc.edu, mt-list@eamt.org
Message-ID:
<CABEbM38d7x5pC5zeENCWWgsN20EpWByBn9+qTBGBrm3DH6NT4Q@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

MT Marathon 2014 and Open Source Convention
http://www.statmt.org/mtm14

Organized and sponsored by MosesCore EU project (http://www.mosescore.eu),
Machine Translation Marathon 2014 is a week-long gathering of machine
translation researchers, developers, students and users. It features:

- MT Lectures and Labs covering the basics and tutorials
- Invited talks from experienced researchers and practitioners
- Technical Talks about open source tools
- Hacking Projects to advance tools or research in one week


The Machine Translation Marathon 2014, MTM2014, will take place in
Trento, Italy in September 8--13th, 2014. It is organised by the the Human
Language Technology group of the Fondazione Bruno Kessler in Trento.

The registration is now open. It's free, but strictly limited to 100
people. For
more information, see: http://www.statmt.org/mtm14

GRANT FOR NEW STUDENTS

Similarly to the past editions, we are pleased to be able to offer up to 6
bursaries to
enable students new to the field to attend the marathon. For more
information, see:
http://www.statmt.org/mtm14/index.php?n=Main.StudentsGrants

Applications should be submitted to the local organisers (mtm2014 AT list
DOT fbk DOT eu) by *July 13th*.

CALL FOR PAPERS

The MT Marathon will again host an Open Source Convention to advance
the state of the art in Machine Translation. We invite developers of open
source tools to present their work and submit a paper of up to 10 pages
that describes the underlying methodology and includes instructions on how
to use the tools.

We are looking for stand-alone tools and extensions of existing tools, such
as the Moses open source system. Accepted papers will be presented during
the MT Marathon and published in the Prague Bulletin of Mathematical
Linguistics, http://ufal.mff.cuni.cz/pbml.html.

Possible Paper Topics:

- Training of Machine Translation models
- Machine Translation decoders
- Tuning of Machine Translation systems
- Evaluation of Machine Translation
- Visualisation, annotation or debugging tools
- Tools for human translators
- Interfaces for web-based services or APIs
- Extensions of existing tools
- Other tools for Machine Translation

Important Dates:

Abstract submission: July 3, 2014 (1 paragraph to
allocate reviewers)
Grant Request: July 13, 2014
Paper submission: July 17, 2014
Notification: July 31, 2014
Camera-ready: August 7, 2014
Deadline for Registration: August 31, 2014
Presentations: September 8--13, 2014
(MT Marathon in Trento)

Instructions for authors and full details are available at the web page
http://www.statmt.org/mtm14.


Looking forward to seeing you in Trento!
the MTM 2014 organizers
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20140526/36346ab8/attachment.htm

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

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


End of Moses-support Digest, Vol 91, Issue 42
*********************************************

Tweet