[TYPES/announce] PhD Studentship in Categorical Natural Language Processing in Queen Mary

Dr Mehrnoosh Sadrzadeh mehrnoosh.sadrzadeh at eecs.qmul.ac.uk
Wed May 8 09:11:54 EDT 2013

We have a fully funded PhD studentship in Queen Mary, starting  September
2013 or January 2014. It will be joint between the Theory and Cognitive
Science groups  of the school and is supervised by Mattew Purver and
Mehrnoosh Sadrzadeh.

The general goals are to exploit the theory and applications of the
categorical compositional distributional models of natural language
semantics; the literature there includes  Coecke-Sadrzadeh-Clark
http://arxiv.org/abs/1003.4394  and Grefenstette-Sadrzadeh 

For details, either click here


or see below:

 Applications are invited for a PhD Studentship starting in September 2013
to undertake research in the emerging field of compositional
distributional semantics. The studentship will include theoretical and
applied research, and will be joint between the Theoretical Computer
Science and Cognitive Science groups.

Distributional models of meaning are based on the insight that meanings of
words depend on the context in which they appear. They lay foundations for
a mathematical model of natural language semantics, where meanings of
words are represented by vectors and word similarity by the distances
between them. These models have proven successful in automatic retrieval
of similar words. Current research examines how such vector
representations might be extended to compounds of words and sentences.
Categorial vector space models, as developed by Clark, Coecke and
Sadrzadeh, are based on Frege’s compositionality principle. They use
syntactic structures and compose word vectors to form compound vectors;
they have been successful in linguistics tasks such as disambiguation.

The proposed project aims to (1) extend this theory to automatable calculi
able to reason about compound similarity, and (2) experiment with the
theory on real corpora and natural language processing tasks (e.g. machine
translation, dialogue modelling, textual entailment). The student will
gain in-depth knowledge of the vector models of meaning, formal models of
language, and natural language processing techniques; she/he will be
encouraged to develop their own research ideas within this broad framework
and present the results in international conferences and workshops.

The student will be based in the School of Electronic Engineering and
Computer Science (www.eecs.qmul.ac.uk) at Queen Mary, University of
London, and will be a member of both the Theoretical Computer Science
(http://theory.eecs.qmul.ac.uk/) and Cognitive Science Groups
(http://cogsci.eecs.qmul.ac.uk/) which have world-leading reputations for
fundamental theoretical work and artificial intelligence, with practical
impact in creating robust reliable software (http://monoidics.com/) and
analysing social media (http://chatterbox.co/).

This studentship, funded by a Queen Mary EPSRC Doctoral Training Account
and an EPSRC Career Acceleration Fellowship is for 3.5 years and will
cover student fees and a tax-free stipend starting at £15,590 per annum.
Further details of the EPSRC scheme see
(www.epsrc.ac.uk/skills/students/dta/Pages/dta.aspx) including terms and
conditions. Applicants must be UK nationals or residents as defined here:

Candidates should have a first class honours degree or equivalent, or a
strong Masters Degree, in Computer Science or a related field, preferably
with some experience in linear algebra, programming, and/or computational
linguistics, and logic. Please contact Dr Mehrnoosh Sadrzadeh
Mehrnoosh.Sadrzadeh at eecs.qmul.ac.uk or Dr Matthew Purver
Matthew.Purver at eecs.qmul.ac.uk if you would like to know more, or have any
queries about how to apply.

To apply please follow the on-line process (see
www.qmul.ac.uk/postgraduate/apply) by selecting “Computer Science” in the
“A-Z list of research opportunities” and following the instructions on the
right hand side of the web page.

Please note that instead of the ‘Research Proposal’ we request a
‘Statement of Research Interests’. Your Statement of Research Interest
should answer two questions: (i) Why are you interested in the proposed
area? (ii)What is your experience in the proposed area? Your statement
should be brief: no more than 500 words or one side of A4 paper. In
addition we would also like you to send a sample of your written work.
This might be a chapter of your final year dissertation, or a published
conference or journal paper. More details can be found at:

The closing date for the applications is 30th. June 2013
IInterviews are expected to take place during July 2013.

More information about the Types-announce mailing list