SÉMAGRAMME and MAGNET are Inria research teams, respectively located in Nancy (France) and Lille (France). SÉMAGRAMME carries out research in natural language processing and mathematics of language, with a focus on semantics and discourse representation. MAGNET carries out research in Machine Learning in information networks, with an important focus on natural language processing and representation learning. In this context, we invite applications from highly motivated MSc holders to pursue research in close collaboration with our permanent research members.
## Job Description
The successful candidate will join the SÉMAGRAMME team led by Philippe de Groote and will contribute to the Inria-DFKI joint project “Improving Embeddings with Semantic Knowledge”. Research will be carried out in collaboration with researchers of the SÉMAGRAMME and the MAGNET teams (ideally spending half time in both teams), and of the German Research Center for Artificial Intelligence (DFKI) in Saarbrücken (Germany).
The overall aim of the project is to integrate lexical and world knowledge into vectorial semantic representations, targeting improvements of high-level NLP tasks like anaphora and coreference resolution. We are in particular interested in developing models that better take into account various types of lexical relations, including the ones expressing collocations, and that can further be enriched by more conceptual embeddings resulting from external knowledge sources.
* A master degree in Computer Science, Natural Language Processing, Mathematics or a related field
* Knowledge and research experience in one or more of the following topics: machine learning, natural language processing, knowledge representation
* Good programming skill, in particular with Python. Familiarity with Pytorch is a plus.
* Fluent written and verbal communication skills in English
* Fixed-term, doctoral contract 3 years
* Starting day: October 2020