Moses-support Digest, Vol 106, Issue 5

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. EMS results - makes sense ? (Vincent Nguyen)
2. Re: blm napalm weights name in ems (Barry Haddow)


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

Message: 1
Date: Mon, 3 Aug 2015 11:00:04 +0200
From: Vincent Nguyen <vnguyen@neuf.fr>
Subject: [Moses-support] EMS results - makes sense ?
To: moses-support <moses-support@mit.edu>
Message-ID: <55BF2D94.3050507@neuf.fr>
Content-Type: text/plain; charset=utf-8; format=flowed

Hi,

Just a heads up on some EMS results, to get your experienced opinions.

Corpus: Europarlv7 + NC2010
fr => en
Evaluation NC2011.

1) IRSTLM vs KenLM is much slower for training / tuning.

2) BLEU results are almost the same (25.7 with Irstlm, 26.14 with KenLM)

3) Compact Mode is faster than onDisk with a short test (77 segments 96
seconds, vs 126 seconds)

4) One last thing I do not understand though :
For sake of checking, I replaced NC2011 by NC2010 in the evaluation (I
know since NC2010 is part of training, should not be relevant)
I got roughly the same BLEU score. I would have expected a higher score
with a test set inculded in the training corpus.

makes sense ?


Next steps :
What path should I use to get better scores ? I read the 'optimize'
section of the website which deals more with speed
and of course I will appply all of this but I was interested in tips to
get more quality if possible.


Thanks





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

Message: 2
Date: Mon, 03 Aug 2015 16:49:26 +0100
From: Barry Haddow <bhaddow@inf.ed.ac.uk>
Subject: Re: [Moses-support] blm napalm weights name in ems
To: John Joseph Morgan <johnjosephmorgan@gmail.com>,
moses-support@mit.edu
Message-ID: <55BF8D86.8070200@inf.ed.ac.uk>
Content-Type: text/plain; charset=UTF-8; format=flowed

Hi John

> Is there a reason the example weight file has this feature name that I?m missing?
My fault I'm afraid. I streamlined bilingual-lm in EMS, but didn't
realise that the example bypassed tuning. I've fixed it now according to
your suggestion,

cheers - Barry

On 02/08/15 15:46, John Joseph Morgan wrote:
> Hello,
> I just wanted to give a heads up that in order to get the ems to run completely with the config.toy.bilinguallm config file I had to make a minor change.
> Instead of tuning the config file points to a file called weight_bilinguallm.ini.
> I changed the feature name ?BilingualNPLM0? to BLMbilingual-lm?.
> I?m running the same setup now with tuning, I?m hoping the feature names get written correctly.
> Is there a reason the example weight file has this feature name that I?m missing?
> Thanks,
> John
>
>
>
> _______________________________________________
> 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.



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

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


End of Moses-support Digest, Vol 106, Issue 5
*********************************************

Tweet