The GRASP project aims at designing new graph-based Machine Learning algorithms that are better tailored to Natural Language Processing structured output problems. Focusing on semi-supervised learning scenarios, we propose to extend current graph-based learning approaches (e.g., label propagation, manifold regularization) along two main directions: (i) the use of structured outputs during inference, and (ii) a graph construction mechanism that is more dependent on the task objective and more closely related to label inference. Combined, these two research strands will provide an important step towards delivering more adaptive (to new domains and languages), more accurate, and ultimately more useful language technologies. We mainly target semantic and pragmatic tasks such as coreference resolution, temporal chronology prediction, and discourse parsing for which proper Machine Learning solutions are still lacking.
Both candidates should have outstanding research track records, including a previous degree (Master/PhD) in computer science (preferably with a specialization in artificial intelligence and/or machine learning), applied mathematics or computational linguistics. Strong programming skills are required. Candidates are also expected to have an excellent command of English, as well as good academic writing and presentation skills.
The gross monthly salary is 3850€ (or 2 132.97€ after taxes) for the Post-doc, and 3 100€ (or 1730€ after taxes) for the PhD student.
Applications should include a detailed curriculum vitae together with a motivation letter, and should be sent to Pascal Denis: pascal.denis at inria.fr.
Deadline for applications: **September 1 st, 2017**.
+++++++++++++++++++++++++++++++++++++++++++++++ Pascal Denis Equipe MAGNET, INRIA Lille Nord Europe Bātiment B, Avenue Heloļse Parc scientifique de la Haute Borne 59650 Villeneuve d'Ascq Tel: ++33 3 59 35 87 24 Url: http://researchers.lille.inria.fr/~pdenis/ +++++++++++++++++++++++++++++++++++++++++++++++ -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 3180 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20170714/9f62f584/attachment.txt>