NAVER LABS Europe Homepage
preloder

university_Prague

EMNLP 2019

3rd - 7th November 2019, Asia World Expo, Hong Kong
We will present 2 papers at the main conference, 6 workshop papers and 1 paper at ConLL.
...
university_Prague

Thirty-third Conference on Neural Information Processing Systems (NeurIPS | 2019 )

8th - 14th December 2019
We will present 2 orals and 2 workshop papers and are looking forward to meeting you at our booth.
...
university_Prague

“Filles et maths : une équation lumineuse” – an event to promote science careers for girls

4th December 2019
Vassilissa Lehoux will be there to encourage girls to pursue science and math careers.
...

R2D2: Repeatable and Reliable Detector and Descriptor

Jérome Revaud, Cesar de Souza, Philippe Weinzaepfel, Martin HumenbergerConference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada, 8-14 December, 2019

Mobile Recommendation within a Strong Privacy Oriented Paradigm

Denys Proux, Frédéric Roulland3rd ACM SIGSPATIAL Workshop on Location-based, Recommendations, Geosocial Networks and Geoadvertizing, Chicago, USA, 5 November, 2019

Machine Translation of Restaurant Reviews: New Corpus for Domain Adaptation and Robustness

Alexandre Berard, Ioan Calapodescu, Marc Dymetman, Claude Roux, Jean-Luc Meunier, Vassilina Nikoulina, Bulent SariyildizWorkshop on Neural Generation and Translation (WNGT), EMNLP, Hong Kong, China, 4 November, 2019

Machine Translation of Restaurant Reviews: New Corpus for Domain Adaptation and Robustness

Alexandre Berard, Ioan Calapodescu, Marc Dymetman, Claude Roux, Jean-Luc Meunier, Vassilina NikoulinaWorkshop on Neural Generation and Translation (WNGT 2019), EMNLP, Hong Kong, China, 4 November, 2019
8 November 2019
EMNLP blog image

EMNLP2019 – what we saw and liked

EMNLP 2019 was in Hong Kong and received a record-breaking number of submissions, but here is a very biased selection of what we liked from the things we saw.
30 October 2019

Predicting when Machine Learning Models Fail in Production

Reducing risks and advancing the decision-making process for Natural language Processing Models in production.
25 October 2019
VSLAM image

SLAMANTIC – Leveraging Semantics to Improve VSLAM in Dynamic Environments

Evaluating our method on public datasets, we show that it can successfully solve challenging situations in dynamic environments which cause state-of-the-art baseline VSLAM algorithms to fail and that it maintains performance on static scenes.

PARTNERS

RESEARCH – EU/GOVT – BUSINESS – ENTREPRENEURS

Our partnerships range from long-term fundamental research to investment in products and services.