Title : Multimodal detection of Fake News Keywords: NLP, multimodal embedding, image/video processing, social networks Full desc: http://www.irisa.fr/offres-emploi/2021-05/multimodal-detection-fake-news Duration: 18 months Contact : vincent.claveau@irisa.fr ewa.kijak@irisa.fr Context === The post-doc will be supervised by Ewa Kijak and Vincent Claveau, IRISA, Rennes, France. The position is to be filled as soon as possible and will end at most in Dec. 2022 (max duration 18 months). Research topics ======= The objective of the project is to propose and implement robust approaches to detect manipulations in documents containing text and images, adapted in particular to social networks. To do so, we wish to exploit multimodal information and contextual information (knowledge base on personalities, publication context). The research questions that arise are the following: How to leverage users' reactions to detect fake news? Which multimodal representations are most suitable to deal with text/image news? How to take advantage of advances on multimodal tasks such as the generation of one modality from another to from another to extract new multimodal representations? What database search strategies should be used? How should the returned results be exploited? How can attention layers be used to highlight the words or regions of the image that contributed the most to the decision? See the full description at http://www.irisa.fr/offres-emploi/2021-05/multimodal-detection-fake-news Qualification and skills ============ The candidate should have: - a PhD in Computer Science, in relation with AI/machine learning - experience of deep learning for NLP and/or IR and/or Computer Vision - programming skills: Python, PyTorch or TensorFlow, HuggingFace - fluency in English is required, French would be appreciated Remuneration ====== Salary according to CNRS pay scale and experience (Annual Gross Salary min. : 31 404 ¤ with charges i.e. about 2100¤ net per month); health insurance is included in salary. Other benefits include subsidized meals and partial reimbursement of public transport costs. How to apply ====== Send your application to vincent.claveau@irisa.fr and ewa.kijak@irisa.fr ; it may include: * a research statement * a curriculum vitae * a list of publications (incl. your PhD thesis) * names of two references Applications will be accepted until the vacancy has been filled, but applications received before June 18 will receive full attention. About the Lab ====== www.irisa.fr IRISA is today one of the largest French research laboratories (more than 850 people) in the field of computer science and information technologies. Structured into seven scientific departments, IRISA is a research center of excellence with scientific priorities such as bioinformatics, systems security, new software architectures, virtual reality, big data analysis and artificial intelligence. Focused on the future of computer science and necessarily internationally oriented, IRISA is at the very heart of the digital transition of society and of innovation at the service of cybersecurity, health, environment and ecology, transport, robotics, energy, culture and artificial intelligence.