One year Postdoctoral position at LINA, Nantes, France

Topic: Cross-lingual Word Sense Disambiguation from comparable corpora


Contact: B. Daille
beatrice.daille_at_univ-nantes.fr

Location: LINA - U. of Nantes- Nantes France
http://www.lina.univ-nantes.fr/

Required education: PhD in Computer Sciences with NLP courses
or in Computational linguistics


The work takes place in the context of the Termith project, funded by
the French National Research founding. The collaborative research
project TermITH (Terminology and Indexation of Texts in the area of
Humanities) deals with information access to textual documents via a
full-text indexing which is based on terms which are detected,
disambiguated and analysed.
TermITH deals with scientific area in which the ambiguity between
terminological and general language usage is very high: the
humanities. Five disciplines will be covered: linguistics, history,
sociology, psychology and archaeology.

TermITH's approach is intended to cross the automatically detected and
disambiguated occurrences of terms in texts with available
interdisciplinary lexicons and terminological resources to isolate the
specific terms for each studied area.
The postdoctoral work will focus on the word-sense and terminological
disambiguation using cross-lingual information. The disambiguation
should be able to distinguish between terminological and language
general senses, and between several terminological entries.  Several
works have demonstrated the validity of using parallel corpora for
bilingual word sense disambiguation.  The use of comparable corpora for
such task has to be investigated. The method will be implemented within
Termith platform, an UIMA framework based on TermSuite.


Termith www.atilf.fr/ressources/termith/
TermSuite http://code.google.com/p/ttc-project/
UIMA http://uima.apache.org/

Skills:
- French working language
- English mandatory
- Java programming
- UIMA knowledge will be a strong plus


The candidate will integrate the NLP team whose main research topic is
language resources and multilingual applications. NLP team developed
open source tools under APACHE 2 licence.

Duration: 12 months starting from 1st of September 2013.
Salary follows French university scales and will depend on the
candidate's experience. The minimal amount salary is around 1900
¤/month.

To apply, please send a CV, a cover letter describing how the candidate
background will contribute to the project and the name of two referees.