Job: 3 PhD Studentships, "Multiple Choice Test Item Generation" at the University of Wolverhampton (Deadline Extension)

Thierry Hamon thierry.hamon at LIPN.UNIV-PARIS13.FR
Fri Apr 6 14:44:09 UTC 2007

Date: Wed, 4 Apr 2007 16:19:10 +0100
From: "Evans, Richard J" <R.J.Evans at>
Message-ID: <1E93EA79FECAE149808363138FAE5BE1051D1E9F at>

With apologies for cross-postings.

(£10,000 first year, £11,000 second year, £12,000 third year)

Closing date: 16th April 2007

The Research Group in Computational Linguistics, University of
Wolverhampton invites applications for three-year-funded PhD
studentships in Computational Linguistics. Three positions will be
available. Successful candidates are expected to carry out work on
multiple-choice test item generation, with their research covering,
but not limited to, one or more of the following areas:

(1) syntactic processing for real-world NLP applications (with
    particular reference to multiple choice time item generation);

(2) development of a multiple choice test item generation system for

(3) proposal of high quality distractors for multiple-choice test
    items in the biomedical domain.

Students involved in area (1) should direct their activities toward
the accurate syntactic-semantic analysis of complex sentences,
proposing a treatment which takes issues such as co-ordination and
punctuation into account. This research will be applied to a
real-world NLP application such as information extraction in the
domain of biomedicine. Area (2) will address the implementation and
tuning of a Spanish-language system that will be drawn from the
existing system for English. A good command of the Spanish language
will be vital for this task together with excellent programming skills
and the ability to develop and harness lexical and ontological
resources in this context. The integration of additional NLP
techniques for Spanish such as named entity recognition or temporal
processing will also be addressed in this area. Research in area (3)
may involve the development of new processing units for entailment
recognition and temporal processing. These units will be used to
derive causal relationships in biomedical texts in order to enhance
the quality of automatically proposed distractors closely related to
the focus of the test items. The student's activities may also include
automatic recognition of textual entailment as well as approaches to
the identification of morphological and lexical similarity.

In their studies, the students will have access to and will benefit
from all the resources developed in an existing related project. This
includes the opportunity to conduct user-evaluation, which will be
very beneficial in the development of the system modules. In return,
part of the PhD work will be integrated in the system to be developed
during the project. Further information on related research can be
found in the papers:

Mitkov, R. and Ha, L. A. (2003): Computer-Aided Generation of
Multiple-Choice Tests. In Proceedings of the HLT-NAACL 2003 Workshop
on Building Educational Applications Using Natural Language
Processing, Edmonton, Canada, May, pp. 17 - 22 ( )

Mitkov, R., Ha, L. A., and Karamanis, N. (2006) A computer-aided
environment for generating multiple-choice test items. Natural
Language Engineering, Volume 12, Issue 02, June 2006, pp 177-194. doi:
10.1017/S1351324906004177, Published online by Cambridge University
Press 22 May 2006. (

We are looking for candidates with a good honours degree in
Linguistics, Computational Linguistics, Computer Science or
Information Sciences, with programming skills and some experience in
Natural Language Processing.

Required skills:

- degree in Linguistics, Computational Linguistics, Computer Science
  or Information Sciences

- experience with at least one of the following: Java, Perl, C, C++, .NET
  knowledge of linguistics with a particular emphasis on syntax and
  the relationship between syntax and semantics.

- experience in Natural Language Processing including real-world
  applications such as information extraction or question answering

- good command of the English language (Areas (1) and (3) or Spanish (2))

Desirable skills:

- Master's degree in Linguistics, Computational Linguistics, Computer
  Science, or Information Sciences

- experience in syntactic parsing, syntactic theory, corpus
  linguistics, and or information extraction

- some familiarity with programming languages such as Perl, C, or

Applications should be sent to

     Mr. Le An Ha
     Research Institute of Information and Language Processing
     University of Wolverhampton
     Stafford St.
     WV1 1SB
     United Kingdom
     E-mail: L.A.Ha at

and must include:

- completed application form available from

- CV

- names, emails, and telephone numbers of three referees

- copy of university degree (in English)

- copy of transcript listing all university marks (in English)

- evidence of postgraduate qualification if applicable

- a covering letter in which candidates explain why they have applied
  for the studentship, give details of their research
  interests/experience, background, programming skills and an outline
  of any experience in Natural Language Processing or Linguistics.

- a PhD plan (about 1000 words) which proposes research questions
  relating to the generation of multiple choice test items to to be
  addressed, the academic or intellectual context in which the
  proposed work is located and the methodology likely to be
  employed. A brief action plan should also be provided. The field of
  this PhD MUST be applicable to the automatic generation of multiple
  choice test items.

Applications should be made by email. The closing date for
applications is 16th April 2007. Short-listed applicants will be
contacted and notified of the specific date of interviews to be held
in April (email and telephone). Successful candidates will have to
register no later than June.

The studentship includes a maintenance grant of 10,000 GBP for the
first year, 11,000 GBP for the second year and 12,000 GBP for the
third year and also covers the tuition fees for 3 years.

The successful candidate will be working in a vibrant research
environment, engaging in active research. This studentship is funded
by an externally funded project, CAID, so it is expected that the
appointed student will contribute to this project as well. In return,
the student will have access and will benefit from the resources
developed in the project.

Wolverhampton ( )

Established by Prof. Mitkov in 1997, the Research Group in
Computational Linguistics is a highly successful one, delivering
cutting-edge research in a number of NLP areas such as anaphora
resolution, automatic summarisation, question answering, lexical
knowledge acquisition, text categorisation, named entity recognition,
information extraction, corpus construction and annotation, automatic
terminology processing, multilingual processing, and multiple-choice
question generation. To a large extent, this research has been
undertaken in projects funded by major UK funding bodies and
commercial partners.

For further information/queries, please contact:
Mr. Le An Ha
Phone: +44 1902 322 623
Email: L.A.Ha at

Richard Evans
Computational Linguistics Research Group
Research Institute of Information and Language Processing
University of Wolverhampton
United Kingdom
R.J.Evans at 

Message diffuse par la liste Langage Naturel <LN at>
Informations, abonnement :
English version       : 
Archives                 :

La liste LN est parrainee par l'ATALA (Association pour le Traitement
Automatique des Langues)
Information et adhesion  :

More information about the Ln mailing list