We are looking for a research engineer with a background in Natural Language Processing, Knowledge Representation and Semantic Web to join the Inria WIMMICS team (http://wimmics.inria.fr). The context is the ALOOF (Autonomous Learning of the Meaning of Objects, https://project.inria.fr/aloof) CHIST-ERA European project. The goal of the project is to enable robots and autonomous systems working with and for humans to exploit the vast amount of knowledge on the Web in order to learn about previously unseen objects. The system can then use this knowledge when involved in human activities and acting in the real world. More precisely, the project scenario consists of an open-ended domestic setting where robots have to find objects. Within this context, the goal of this engineering position is to go beyond the current-state-of-the-art in knowledge acquisition for cognitive systems by developing and combining techniques from text mining to allow robots to engage in life-long learning from the Web. Techniques that can harvest the Web to extract symbolic knowledge about objects and their characteristics from unstructured text (relying on natural language processing and machine reading techniques), as well as available ontologies and knowledge on the Semantic Web will be developed, grounding this knowledge in visual features so that robots can recognize these objects in a real situation. Given that the project is in its second year, we are ready to consolidate and integrate the research work done so far into high quality deliverables such as software and resources. In particular, the following tasks will be addressed: - Building a visual object category knowledge base and consolidate the semantic object knowledge base created so far, relying on basic ontological knowledge about objects extracted by analyzing unstructured and structured information sources on the Web following the learning by reading paradigm [1]. - Support the acquisition of semantic knowledge concerning object properties and relations from the web [2,3]. - Cross-modal learning starting from labels of unconstrained data, to efficiently acquire knowledge about an unknown object that has been encountered in real time. - Integration with the work from the other project partners, in particular bridging the semantic and visual object knowledge extracted from Web resources and the robot sensors. *Profile* Mandatory requirements for applicants: 1. PhD or MSc in Computer Science; 2. Experience in NLP, Knowledge Representation, Semantic Web, or in a related field (Artificial Intelligence, Machine Learning...); 3. Hands-on experience of one or more of the following programming languages (Python, Java) and technologies (XML, JSON, RDF/OWL, RESTful Web services, *nix systems, scripting tools); 4. Fluent English is mandatory to work in an international team and to exchange with the project European partners; Project duration: 18 months Deadline: open until filled Working environment: the engineer will be employed at Inria Sophia Antipolis, France, in the Wimmics team Salary: Gross Salary per month according to the level of diploma and the experience in the domain: 2500 - 2800¤ / month (corresponding to 2100-2300¤ net salary / month) Contact email: Elena Cabrio: elena.cabrio@unice.fr; Fabien Gandon: fabien.gandon@inria.fr [1] Valerio Basile, Elena Cabrio, Claudia Schon, KNEWS: Using Logical and Lexical Semantics to Extract Knowledge from Natural Language, ECAI 2016 (poster paper). [2] Valerio Basile, Elena Cabrio, Fabien Gandon, Building a General Knowledge Base of Physical Objects for Robots, ESWC 2016 poster paper (http://2016.eswc-conferences.org/sites/default/files/papers/Accepted%20Posters%20and%20Demos/ESWC2016_POSTER_Building_A_General_Knowledge_Base.pdf). [3] Jay Young, Valerio Basile, Lars Kunze, Elena Cabrio, Nick Hawes. Towards Lifelong Object Learning by Integrating Situated Robot Perception and Semantic Web Mining, ECAI 2016.