Postdoctoral position in deep learning (computer vision and natural
language processing) at Paris

 

The CEA LIST is seeking a postdoctoral researcher in the context of a
collaboration with the CNRS LIMSI, both being located at the Saclay
University, 15km south of Paris, France. Within the CEA LIST, our
laboratory gathers around 70 people (half are permanent researchers,
the others are Post doc and PhD candidates) working in the field of
computer vision and natural language processing.

 

In the domain of Information Extraction, the Entity Disambiguation
task (or Entity Linking) consists in connecting an entity extracted
from a text to known entities in a knowledge base, which is useful for
further extraction tasks (relation extraction or event detection, for
instance) or to provide a unique normalization of the entities in an
Information Retrieval context. On nowadays, actual Entity Linking,
with regard to millions of instances in the knowledge base, is only
applied to textual content. The proposed postdoc consists in exploring
the usage of visual information to improve such a task. It thus
relates to both computer vision and natural language processing and
the candidate will work with researchers of both domains, relying on
machine learning and deep learning methods.

 

Several track of research can be considered. A classical Entity
Linking system is made of three main modules. First, it analyzes an
input (query) to identify an "entity mention" that needs to be linked
to the knowledge base. Second, for each mention, the system generates
several candidate entities from the knowledge base and finally, it
selects the best entity among the candidates. The proposed position
deals with the second and the third module. In practice, two possible
contributions can be considered. The first relates to the case of a
multimodal query, with both visual and textual content. It will
consists in mixing these piece of information, for instance by relying
on the fact that they usually both result from the usage of deep
neural architectures. The second possible contribution can be applied
to a pure textual query, since its objective is to enrich the
knowledge database with implicit visual links between the entities
that will improve the second module of the system.

 

An ideal candidate should possess (or be near completion of) a
doctoral degree in computer vision, machine learning or natural
language processing together with a solid mathematical background,
good programming skills and a strong academic publication record. The
starting date is early 2018. The contract is for a 1-year fixed-term
period with a possibility for an extension.

 

Please apply by sending by mail a CV, a focused motivation letter and
one to three recommendation letters to herve.le-borgne@cea.fr and
bg@limsi.fr. The salary depends on the diploma and experience and will
be given on demand from the CV.

 

---

Laboratory website : http://www.kalisteo.eu/en/index.htm

Hervé le Borgne : https://sites.google.com/site/hleborgne/

Brigitte Grau : https://perso.limsi.fr/bg/PageBrigitteGrau-en.html