POSTDOCTORAL/ENGINEERING POSITION at INRIA Rennes, France

Topic: Text-mining and information extraction in multimedia documents

Information extraction and text-mining are well known domains of Natural
Language Processing. Yet, dealing with low-quality texts, like automatic
speech transcription or OCRized overlays, raises new challenges in terms
of portability and robustness.

In that context, the proposed project aims at developing new text-mining
and information extraction approaches to overcome these
difficulties. The goal is to rely on simple but robust description of
the text and new machine learning techniques and paradigms (CRF,
boosting, semi-supervised approaches...).

The typical tasks concerned are term and named entity recognition and
discovery, (ontological or semantic) relation recognition and
discovery...

The candidate is expected to implement these new approaches, participate
to evaluation and challenges in this field, both for well-formed texts
and degraded texts (such as speech transcripts), and may also help in
developing new evaluation datasets.

This work takes place in the context of the Quaero project, funded by
the French National Innovation Agency (www.quaero.org).
The work will be performed at IRISA/INRIA Rennes, France
(http://www.irisa.fr/http://www.inria.fr/centre/rennes/). The candidate
will integrate the TexMex team, whose main research topics include
large-scale multimedia indexing, speech processing, information
retrieval.

QUALIFICATIONS AND POSITION

The successful candidate will have a engineering degree or PhD with a
track record of Information Extraction, Text-Mining or Machine Learning
for Natural Language Processing research.

Fluency in English is mandatory.

This position is for 12 months and may begin as early as Nov 1st, 2012,
and no later than mid-December. Salary follows INRIA scales and depends
on the candidate's experience (the minimum monthly net salary is about
1900 ¤).

To apply, please send a cover letter, describing how the applicant's
knowledge and research background will contribute to the project, a CV,
and the names and contact information of two referees to:

Vincent Claveau (vincent.claveau at irisa.fr)