Master/PhD Internship – Deep Machine Reading
NAVER LABS Europe's mission is to advance the state-of-the-art in Ambient Intelligence, while paving the way for these innovations into a number of NAVER flagship products and services. This includes research in models and algorithms to give humans faster and better access to data and to allow them to interact with technology in simpler and more natural ways.
In this context, the field of Machine Reading has recently emerged as a possible continuation of the tasks of Natural Language Processing. Given a large set of passages of text associated with questions and answers, our goal consists of learning a question answering system solely from these examples. As research groups dedicated to Machine Reading around the globe have started to produce encouraging results, this task challenges our current understanding of deep learning and machine comprehension.
In this internship, the successful candidate will be involved in the design and development of novel models for machine comprehension applied at the scale of NAVER in the context of electronic encyclopedia and social media understanding. Finally, at NAVER LABS we encourage participation in the academic community. Our researchers collaborate closely with universities and regularly publish in venues such as ACL, EMNLP, KDD, SIGIR, ICML and NIPS.
- Master and/or Ph.D. in machine learning with a strong interest in Deep Learning.
- Knowledge of statistical and deep learning application to NLP.
- Strong development skills of relevant frameworks like pytorch and/or tensorflow.
- Gated End-to-End Memory Networks , Fei Liu and Julien Perez, EACL 2017
- Dialog State Tracking, a machine reading approach using memory networks , Julien Perez and Fei Liu, EACL 2017
- ReviewQA: a relational aspect-based opinion reading dataset , Quentin Grail and Julien Perez, CAP’2018