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.

Specific requirements:

The starting date is early 2018. The contract is for a 1-year fixed-term period with a possibility for an extension.

Educational level:

Ph. D.

Tagged as: , , , , ,

About Cowichan Energy Alternatives

Cowichan Energy Alternatives (CEA) was founded in 2008 as a non-profit organization focused on providing energy and greenhouse gas (GHG) emissions inventories and planning services, renewable energy feasibility studies and implementation, and leading community carbon offsetting initiatives through Community Carbon Marketplace (CCM). CEA's innovative not-for-profit approach is focused on finding creative solutions to energy and emissions challenges while maximizing triple bottom line benefits to sustainability partners and the community. Funds generated through CEA's GHG inventory and other revenue-generating sustainability services go to support educational initiatives and a growing list of alternative energy projects and carbon offsetting services that truly demonstrate leadership by example.

Our first and largest alternative energy implementation project to date is the development of a biofuel production and distribution facility at Bing's Creek in partnership with the Cowichan Bio-Diesel Co-op (Co-op)