Resource Efficient Neural Machine Translation through Quantization and Distillation - Naver Labs Europe
loader image
4 October 2019
Meylan, France
Job Type
Start date
February 2020
5-6 months


Neural Machine Translation (NMT) has made impressive progresses in the past few years.  The current state-of-the-art model for NMT (and NLP in general) is the Transformer  [Vaswani  et al.,  2017], which is however costly to train and develop both financially and environmentally [Strubell  et  al. 2019]. Such large neural networks are also problematic to deploy in resource restricted environments and for real-time production due to their  low inference time efficiency.
To overcome these issues, two complementary approach are often used: model distillation [Hinton et al. 2015], applied in NLP for example in Tang et al. [2019] and Jiao et al [2019], as well as Ding et al., [2019], Takashima et al., [2019] for ASR; and model quantization [Shen et al 2019, Aji & Heafield 2019].
​Naver Labs Europe and LIG (computer science lab at UGA) is looking for a motivated and independent intern to develop and experiment with both approaches as applied to NMT.
S.he will work with public data (eg: WNGT 2019 efficiency task) as well as in-house data.
Publication of the results in a top-tier conference is highly encouraged.
 - student currently enrolled in a university, either at research master or PhD level

Required skills

- Knowledge of deep learning as applied to NLP
- Good coding skills, including at least one of the major deep learning toolkits (preferably Pytorch
- Data manipulation (textual data) and python programming

Application instructions

Please note that applicants must be registered students at a university or other academic institution and that this establishment will need to sign an 'Internship Convention' with NAVER LABS Europe before the student is accepted.

You can apply for this position online. Don't forget to upload your CV and cover letter before you submit. Incomplete applications will not be accepted.


NAVER LABS is a world class team of self-motivated and highly engaged researchers, engineers and interface designers collaborating together to create next generation ambient intelligence technology and services that are rich with the organic understanding they have of users, their contexts and situations.

Since 2013 LABS has led NAVER’s innovation in technology through products such as the AI-based translation app ‘Papago’, the omni-tasking web browser ‘Whale’, the virtual AI assistant ‘WAVE’, in-vehicle information entertainment system ‘AWAY’ and M1, the 3D indoor mapping robot.

The team in Europe is multidisciplinary and extremely multicultural specializing in artificial intelligence, machine learning, computer vision, natural language processing, UX and ethnography. We collaborate with many partners in the European scientific community on R&D projects.

NAVER LABS Europe is located in the south east of France in Grenoble. The notoriety of Grenoble comes from its exceptional natural environment and scientific ecosystem with 21,000 jobs in public and private research. It is home to 1 of the 4 French national institutes in AI called MIAI (Multidisciplinary Innovation in Ai) It has a large student community (over 62,000 students) and is a lively and cosmopolitan place, offering a host of leisure opportunities. Grenoble is close to both the Swiss and Italian borders and is the ideal place for skiing, hiking, climbing, hang gliding and all types of mountain sports.

Drop files here browse files ...
Are you sure you want to delete this file?