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. The CEA LISTgathers 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. The CNRS LIMSI (UPR3251) is a CNRS laboratory tightly associated with Paris-Sud University. LIMSI also develops collaborations with other universities and Engineering schols within the University Paris-Saclay. This pluri-disciplinary research laboratory gathers academics and scholars from various scientific fields: primarily from the Engineering and Information Sciences, but also from Cognitive Science and Linguistics.
The postdoc is funded by DIGICOSME, an excellence laboratory center (labex) in the field of computer science and communication.
The post-doc deals with the disambiguation of visual and textual content, in the context of an Entity Disambiguation task, also known as Entity Linking. It consists in connecting an entity extracted from a document to known and unique entities in a knowledge base. On nowadays, actual Entity Linking, with regard to millions of instances in the knowledge base, is only applied to textual content. The proposed post-doc consists in exploring the usage of visual information to improve the disambiguation. 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 approaches. In particular, a core problem is that of the design of a textual/visual joint space in the same as those used in visual question answering and automatic image captioning.
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 first semester 2018 (before July 2018) The contract is for a 1-year period with a possible extension.
(c) GdR 720 ISIS - CNRS - 2011-2018.