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: MERT: process n-best list before mert (Jorg Tiedemann)
----------------------------------------------------------------------
Message: 1
Date: Sun, 23 Apr 2017 10:05:00 +0300
From: Jorg Tiedemann <tiedeman@gmail.com>
Subject: Re: [Moses-support] MERT: process n-best list before mert
To: Ergun Bicici <bicici@gmail.com>
Cc: moses-support <moses-support@mit.edu>
Message-ID: <DABA7F02-7728-49E6-BBC1-A6944073EEF6@gmail.com>
Content-Type: text/plain; charset="utf-8"
Yes, true, I added that for an older version of mert but it changed a lot since then and I was too lazy to look for the best place in the latest script. That?s also why I?d like to include the option in the official repository now. I?ll do that now ...
J?rg
> On 23 Apr 2017, at 00:27, Ergun Bicici <bicici@gmail.com> wrote:
>
>
> Dear Jorg,
>
> I encountered similar issue for my character SMT experiments concurrently looking at your paper (http://aclanthology.info/papers/combining-word-level-and-character-level-models-for-machine-translation-between-closely-related-languages <http://aclanthology.info/papers/combining-word-level-and-character-level-models-for-machine-translation-between-closely-related-languages>) and added a line to call a script before the gzip of the nbest file within the MERT main loop.
>
> At the end of section 2, you mention that:
> "
> <image.png>
> " Preslav Nakov <http://aclanthology.info/people/preslav-nakov-5181> | J?rg Tiedemann <http://aclanthology.info/people/jorg-tiedemann-3696>
> Anthology:
> P12-2059
> Volume:
> Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) <http://aclanthology.info/volumes/proceedings-of-the-50th-annual-meeting-of-the-association-for-computational-linguistics-volume-2-short-papers>
> Authors:
> Preslav Nakov <http://aclanthology.info/people/preslav-nakov-5181> | J?rg Tiedemann <http://aclanthology.info/people/jorg-tiedemann-3696>
> Month:
> July
> Year:
> 2012
> Venue:
> ACL <http://aclanthology.info/venues/acl>
> Address:
> Jeju Island, Korea
> SIG:
>
> Publisher:
> Association for Computational Linguistics
> Pages:
> 301?305
> URL:
> http://aclweb.org/anthology/P12-2059 <http://aclweb.org/anthology/P12-2059>
>
> Regards,
> Ergun
>
> On Sat, Apr 22, 2017 at 8:41 PM, Hieu Hoang <hieuhoang@gmail.com <mailto:hieuhoang@gmail.com>> wrote:
> sounds good. You're always welcome to check it in yourself as long as you look after it. Send me your github username or create a git pull request
>
> * Looking for MT/NLP opportunities *
> Hieu Hoang
> http://moses-smt.org/ <http://moses-smt.org/>
>
>
> On 22 April 2017 at 15:44, Jorg Tiedemann <tiedeman@gmail.com <mailto:tiedeman@gmail.com>> wrote:
>
> Great - thanks. I modified a little to make it possible to pass a command to the new option.
> I hope I didn?t break anything. Maybe this modification could become part of the official moses package?
>
> J?rg
>
> J?rg Tiedemann
> tiedeman@gmail.com <mailto:tiedeman@gmail.com>
>
>
>
>
>
>
>
>> On 22 Apr 2017, at 15:50, Anoop (?????) <anoop.kunchukuttan@gmail.com <mailto:anoop.kunchukuttan@gmail.com>> wrote:
>>
>> Hi Jorg,
>>
>> I had made changes to mert-moses.perl to achieve exactly what you are looking for. Please find the script attached.
>>
>> To enable character level to word level transformation, you have to pass the option '--transform-decoded-file' tomert-moses.pl <http://mert-moses.pl/>
>> The script assumes that a caret token '^' has been added between words while preprocessing the corpora. So, all subwords between two carets are merged to create a single word. The changes are on line 826--834.
>>
>> Regards,
>> Anoop.
>>
>>
>>
>> On Sat, Apr 22, 2017 at 5:10 PM, Jorg Tiedemann <tiedeman@gmail.com <mailto:tiedeman@gmail.com>> wrote:
>> Hi,
>>
>> Is there an easy way to integrate a small script to process n-best lists in mert-moses.perl before running mert at each iteration? An example would be to merge character-level translations to run mert on word-level segmentations. It?s probably rather straightforward to add an option to specify a script for filtering but it may already exist and I just don?t see it?
>>
>> Thanks!
>> J?rg
>>
>> **********************************************************************************************
>> J?rg Tiedemann
>> Department of Modern Languages http://blogs.helsinki.fi/tiedeman/ <http://blogs.helsinki.fi/tiedeman/>
>> University of Helsinki http://blogs.helsinki.fi/language-technology/ <http://blogs.helsinki.fi/language-technology/>
>>
>>
>>
>> _______________________________________________
>> Moses-support mailing list
>> Moses-support@mit.edu <mailto:Moses-support@mit.edu>
>> http://mailman.mit.edu/mailman/listinfo/moses-support <http://mailman.mit.edu/mailman/listinfo/moses-support>
>>
>>
>>
>>
>> --
>> I claim to be a simple individual liable to err like any other fellow mortal. I own, however, that I have humility enough to confess my errors and to retrace my steps.
>>
>> http://flightsofthought.blogspot.com <http://flightsofthought.blogspot.com/><mert-moses.pl <http://mert-moses.pl/>>_______________________________________________
>> Moses-support mailing list
>> Moses-support@mit.edu <mailto:Moses-support@mit.edu>
>> http://mailman.mit.edu/mailman/listinfo/moses-support <http://mailman.mit.edu/mailman/listinfo/moses-support>
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu <mailto:Moses-support@mit.edu>
> http://mailman.mit.edu/mailman/listinfo/moses-support <http://mailman.mit.edu/mailman/listinfo/moses-support>
>
>
>
>
>
> --
>
> Regards,
> Ergun
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20170423/4b6acb76/attachment.html
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 126, Issue 31
**********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 126, Issue 31"
Post a Comment