Moses-support Digest, Vol 87, 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. Readership in Statistical Machine Translation (Bonnie Webber)
2. Tuning hyperparamters with MERT (Prashant Mathur)


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

Message: 1
Date: Thu, 16 Jan 2014 18:31:41 +0000
From: Bonnie Webber <bonnie@inf.ed.ac.uk>
Subject: [Moses-support] Readership in Statistical Machine Translation
To: corpora@uib.no, moses-support@MIT.EDU, moses-developers@MIT.EDU
Message-ID: <20140116183141.696246a1ae9pn4w0@www.staffmail.ed.ac.uk>
Content-Type: text/plain; charset=ISO-8859-1; DelSp="Yes";
format="flowed"

University of Edinburgh
School of Informatics

READERSHIP (ASSOCIATE PROFESSOR) IN STATISTICAL MACHINE TRANSLATION

Applications are invited for the position of Reader (approximately
equivalent to Associate Professor) in Statistical Machine Translation
in the School of Informatics at the University of Edinburgh. The
successful candidate will enjoy the company of researchers from the
Institute for Language, Cognition and Computation (ILCC), one of the
largest research groupings in natural language processing,
computational linguisitcs, spoken language processing, and cognitive
science. Candidates should have a well-established international
research reputation and be willing to undertake original research and
lead a research team in Statistical Machine Translation, in addition
to teaching within the School of Informatics.

Application deadline:
17 February 2014

Further details, and to apply:
https://www.vacancies.ed.ac.uk/pls/corehrrecruit/erq_jobspec_version_4.jobspec?p_id=024457

Informal queries:
Prof Johanna Moore (j.moore@ed.ac.uk) or Prof Steve Renals (s.renals@ed.ac.uk)


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




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

Message: 2
Date: Fri, 17 Jan 2014 17:10:23 +0100
From: Prashant Mathur <prashant@fbk.eu>
Subject: [Moses-support] Tuning hyperparamters with MERT
To: Moses <moses-support@mit.edu>
Message-ID: <52D955EF.6050806@fbk.eu>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed

Hi All,

I am tuning the standard models with an extended feature.
As far as I understood, we can tune only the feature weights in mert.
In my case I have some more hyper parameters that I want to tune
together with the feature weights .. for example. feature learning rate.
Once the nbest-list is created these parameters cannot have any effect
on the list, but they are useful for generating a better nbest-list.
Is there a way to tune all the parameters and hyper parameters together?

Thanks,
Prashant

PS: Till now I was tuning these hyper parameters using Simplex.


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

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


End of Moses-support Digest, Vol 87, Issue 42
*********************************************

Tweet