Moses-support Digest, Vol 115, Issue 11

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. PhD studentship in NLP approaches to estimating text
difficulty (Rohit Gupta)
2. Best alignment algorithm (haouarid@iro.umontreal.ca)
3. Re: Best alignment algorithm (Barry Haddow)


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

Message: 1
Date: Tue, 10 May 2016 20:27:45 +0200
From: Rohit Gupta <enggrohitgupta@gmail.com>
Subject: [Moses-support] PhD studentship in NLP approaches to
estimating text difficulty
To: moses-support@mit.edu, mt-list@eamt.org
Message-ID:
<CAB-CSF8+10DL0OgT3wqHw2_c7TNLVdb5c7wqksz638gUhSGXYA@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

Apologies for any duplicates.

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



PhD studentship in NLP approaches to estimating text difficulty

===================================================



Research Group in Computational Linguistics (Research Institute of
Information and Language Processing), University of Wolverhampton



*** Closing date 23 May 2016 ***





The Research Group in Computational Linguistics (http://rgcl.wlv.ac.uk) at
the Research Institute of Information and Language Processing of the
University of Wolverhampton invites applications for a 3-year University of
Wolverhampton PhD studentship in the area of estimating text difficulty.
The proposed topic of the PhD research will be to develop a Natural
Language Processing (NLP) methodology to predict text difficulty not only
at the grammatical level (e.g. lexical or syntactic complexity) but also at
the level of text content: the complexity of concepts mentioned in a
specific text and the relationships between those concepts. Much of the
research on quantifying text complexity so far has relied on readability
measures which have often been criticised for being inaccurate or
unreliable.



The developed methodology will be applied to a user scenario, e.g. student
assessment.



This is a funded bursary which will consist of a stipend towards living
expenses (?14,500 per year) and remission of fees.





Entry requirements

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



A successful applicant must have:



- A good honours degree or equivalent in Computer Science,
Computational Linguistics or Linguistics, with strong programming skills
and statistical / mathematical background

- Experience in Computational Linguistics / Natural Language
Processing, including Machine Learning approaches to Natural Language
Processing.



Experience in linguistics, particularly psycholinguistics or clinical
linguistics, would be a plus.





Application procedure

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



Applications must include:



- Curriculum vitae listing degrees awarded, courses covered and
marks obtained, publications, relevant experience and names of three
referees who could be contacted for a reference

- Cover letter with statement of research interests, outlining why
you are interested in this PhD position/topic, how you plan to approach the
research task and why you consider your experience to be relevant.

- Expression of interest form which can be obtained by emailing
y.skalban@wlv.ac.uk





Schedule

----------



The application deadline is *23 May 2016*. The short-listed candidates will
be notified by email by *1 June 2016 *and interviewed via Skype on *7 June
2016*. The starting date of the PhD position is 1 October 2016 or any time
as soon as possible after that.



Established by Prof Mitkov in 1998, the research group in Computational
Linguistics delivers cutting-edge research in a number of NLP areas. The
results from the UK research assessment exercises confirm the research
group in Computational Linguistics as one of the top performers in UK
research with its research defined as ?internationally leading,
internationally excellent and internationally recognised?.



Informal enquiries and electronic applications can be sent to by email to:



Prof. Dr. Ruslan Mitkov

Director of the Research Institute of Information and Language Processing

University of Wolverhampton

Email: R.Mitkov@wlv.ac.uk



*Please copy your email or application to Prof. Mitkov?s PA
(y.skalban@wlv.ac.uk <y.skalban@wlv.ac.uk>)*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20160510/92404d9f/attachment-0001.html

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

Message: 2
Date: Tue, 10 May 2016 18:51:43 -0400
From: haouarid@iro.umontreal.ca
Subject: [Moses-support] Best alignment algorithm
To: moses-support@mit.edu
Message-ID:
<2bef1a32200f2d8d0be92cd0bbc17ddc.squirrel@webmail.iro.umontreal.ca>
Content-Type: text/plain;charset=iso-8859-1

Hi,

In moses, there is several alignment algorithms like grow-diag-final-and,
grow-diag-final etc.
Alignment has impact on the extracted phrases and then on the translation
quality.
My question is: what is the best alignment algorithm among those available
in Moses? Is there an article comparing the performance of the several
alignment algorithms.

Thank you,

Dorra


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

Message: 3
Date: Wed, 11 May 2016 08:56:52 +0100
From: Barry Haddow <bhaddow@staffmail.ed.ac.uk>
Subject: Re: [Moses-support] Best alignment algorithm
To: haouarid@iro.umontreal.ca, moses-support@mit.edu
Message-ID: <5732E5C4.7030309@staffmail.ed.ac.uk>
Content-Type: text/plain; charset=windows-1252; format=flowed

Hi Dorra

I think this is the classic paper

http://dl.acm.org/citation.cfm?id=778824

Although a quick google turned up this paper, which is more specific to
your question

http://www.mt-archive.info/MTS-2007-Wu.pdf

cheers - Barry

On 10/05/16 23:51, haouarid@iro.umontreal.ca wrote:
> Hi,
>
> In moses, there is several alignment algorithms like grow-diag-final-and,
> grow-diag-final etc.
> Alignment has impact on the extracted phrases and then on the translation
> quality.
> My question is: what is the best alignment algorithm among those available
> in Moses? Is there an article comparing the performance of the several
> alignment algorithms.
>
> Thank you,
>
> Dorra
> _______________________________________________
> 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 115, Issue 11
**********************************************

Tweet