[Elsnet-list] Paris-Orsay: Job -- Spanish Web text mining at LIMSI

Pierre Zweigenbaum pz at limsi.fr
Sun Oct 25 01:04:49 CEST 2009

Job offer, November 2009 -- October 2011:

LIMSI-CNRS seeks to hire a person skilled in both computer science and
natural language processing who is fluent in Spanish.
The person will work in an International Consortium of teams from
Argentina, Colombia, Uruguay and France on a project funded by the
European Union called CIDESAL
(http://www.msh-m.fr/rubrique.php3?id_rubrique=315), and will be
responsible for its text-mining program. The job offer concerns the
period from November 2009 to October 2011. The contract is for one year
and will be renewed by mutual agreement for the second year.


The goal of the project is to identify and localize Diaspora Knowledge
Networks (DKN). DKN are self-organizing social structures composed of
highly qualified professionals who actively use Internet to mobilize
resources for projects aimed at contributing to the economic and
social development of their home countries. Methods for mining the Web
have to be developed to detect and describe these DKN.

Among the tasks involved are those aimed at creating relevant document
corpora from the Web for characterizing the structure and organization
of a DKN; developing Spanish natural language processing techniques
for identifying subject content, the nature and direction of on-going
collective activity, and the context of cooperation. This type of work
falls in the field of computer supported cooperative work. It

 - skills in Computer Science: Perl, C or another language, MySQL,
 - skills in Natural Language Processing: preferably classification,
   data extraction and text-mining;
 - fluency in Spanish.


LIMSI (Laboratoire d’Informatique pour la Mécanique et les Sciences de
l’Ingénieur) is located in the South of Paris on the Orsay University
campus, and is run by the French National Research Council (CNRS). It
carries out fundamental research on information processing by
combining cognitive science, engineering and social science theories
and approaches (www.limsi.fr). The two teams specifically involved in
the DKN project at LIMSI work on Web corpus detection and processing
and in social informatics. For more information on these two programs

Information in French on this job offer can be found at the following


Candidates with a Masters Diploma or a Doctorate can send their CV’s
by Email to William Turner <william.turner at limsi.fr>.

Salaries will be determined on the basis of the candidate’s diploma
and the CNRS wage scale.

More information about the Elsnet-list mailing list