Moses-support Digest, Vol 97, Issue 8

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: Moses Acknowledge (Hieu Hoang)
2. Re: Combine models with backoff (Tomas Fulajtar)


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

Message: 1
Date: Thu, 6 Nov 2014 23:40:12 +0000
From: Hieu Hoang <Hieu.Hoang@ed.ac.uk>
Subject: Re: [Moses-support] Moses Acknowledge
To: i.ramadan@saudisoft.com
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CAEKMkbgAbnisHiH1=qzFKX-ZPJp-14avk=9utT9jd_tCLh5PhA@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

I believe all moses process return 0 on success, and non-0 on failure. This
is the standard convention.

you should also check that the process hasn't crashed, in which case it
doesn't return any value


On 28 October 2014 09:08, Ihab Ramadan <i.ramadan@saudisoft.com> wrote:

> Dears,
>
> Is there any acknowledge from Moses after completing processes like
> training or tuning something like return code which I can use in my web
> application to tell the user that the process has completed or failed
>
> Thanks
>
>
>
> Best Regards
>
> *Ihab Ramadan*| Senior Developer| Saudisoft <http://www.saudisoft.com/> -
> Egypt | *Tel * +2 02 330 320 37 Ext- 0 | Mob+201007570826 | Fax
> +20233032036 | *Follow us on *[image: linked]
> <http://www.linkedin.com/company/77017?trk=vsrp_companies_res_name&trkInfo=VSRPsearchId%3A1489659901402995947155%2CVSRPtargetId%3A77017%2CVSRPcmpt%3Aprimary>* |
> **[image: ZA102637861]*
> <https://www.facebook.com/pages/Saudisoft-Co-Ltd/289968997768973?ref_type=bookmark>* |
> **[image: ZA102637858]* <https://twitter.com/Saudisoft>
>
>
>
> _______________________________________________
> 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/20141106/49934593/attachment-0001.htm
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image002.gif
Type: image/gif
Size: 1317 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20141106/49934593/attachment-0003.gif
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.gif
Type: image/gif
Size: 1314 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20141106/49934593/attachment-0004.gif
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image003.gif
Type: image/gif
Size: 1351 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20141106/49934593/attachment-0005.gif

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

Message: 2
Date: Fri, 7 Nov 2014 11:29:07 +0000
From: Tomas Fulajtar <TomasFu@moravia.com>
Subject: Re: [Moses-support] Combine models with backoff
To: Hieu Hoang <hieuhoang@gmail.com>, "moses-support
(moses-support@mit.edu)" <moses-support@mit.edu>
Message-ID:
<ee275844de3c45608bc03e8de4fcc58a@BY1PR0201MB0965.namprd02.prod.outlook.com>

Content-Type: text/plain; charset="us-ascii"

Hi Hieu,

I see, it does make sense - thanks for an explanation. The process works as you suggested.

Tomas

From: Hieu Hoang [mailto:hieuhoang@gmail.com]
Sent: Friday, October 31, 2014 4:35 AM
To: Tomas Fulajtar; moses-support (moses-support@mit.edu)
Subject: Re: [Moses-support] Combine models with backoff

you cannot backoff LM in the same way you can with phrase-tables. You can specify both LMs, and they will both be used to score each translation. They will both be tuned by MERT. It usually works ok

On 27/10/14 16:49, Tomas Fulajtar wrote:
Hi all,

I would like to combine two phrase based engines. One, smaller is trained on desired domain data, but with limited corpus size. The second is the legacy one with huge phrase table and LM, but with kind of older/more obsolete terminology. Thus the idea is to combine both to preserve domain/language style from the first engine, but also reduce OOV with application of the second engine.

I think what I am looking for is the Back-off model - use the small one as a preferred one , and then the second in case of phrases not found. I have setup such a config in accordance with http://www.statmt.org/moses/?n=Moses.AdvancedFeatures#ntoc25,.

[feature]
PhraseDictionaryCompact name=A
PhraseDictionaryCompact name=BackOff

[mapping]
0 T 0
1 T 1

[decoding-graph-backoff]
0
1

[weight]
A = 0 0 0 0
BackOff = 0 0 0 0

And it seems to work (weights were tuned afterwards with mert).

I have also read the http://comments.gmane.org/gmane.comp.nlp.moses.user/10099. However there is not mentioned how the LMs combination could be managed. I can add both to ini file and perform the weights tuning, or is it better to set the weights manually? I believe that phrase table backoff would ensure the preference of model A terminology, while combination of both LMs would make the translation smoother as it can benefit from the second, bigger LM.

Could you please correct my assumptions? I hope the explanation does make some sense...

Thank you very much,

Tomas




_______________________________________________

Moses-support mailing list

Moses-support@mit.edu<mailto: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/20141107/c03144f9/attachment.htm

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

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


End of Moses-support Digest, Vol 97, Issue 8
********************************************

Tweet