Reinforcement Learning for Document Layout Analysis - Internship - Naver Labs Europe
NAVER LABS Europe
Published
9 November 2020
Location
Meylan, Grenoble, France, France
Category
Start date
ASAP
Duration
6 months

Description

Document Layout Analysis (DLA) aims at associating to a page image, a structured output corresponding to the hierarchical structure(s) of the page (its regions) and aims also at categorizing these regions (such as line, paragraphs, headings).

While Structured Machine Learning provides some tools to capture context (such as Graph Neural Networks recently [1]), decisions are eventually taken at very low level (input units: pixels, words), and post-processing is often required and often task-specific.

Ideally, a structured output (a graph in general) should be directly generated by the method.

In order to tackle this structured output problem, we would like to learn how to mimic what a human being does when creating ground-truth material for these tasks. The human annotation is composed of a sequence of operations, which can be learned by a system, especially a Reinforcement Learning (RL) system.  The agent (in terms of RL) will play the role of the human annotator, and perform actions the a human annotator will do in order to create ground truth data.

A similar approach was recently tested on the problem of chip design [1]. This problem may be considered, to a certain extent, as being similar to document layout problems.

We expect the intern to design a first prototype using public and in-house datasets.

Required skills

- very good programming skills (python)
- deep knowledge of Neural Network tools (pytorch)
- a first experience on RL is highly recommended

References

[1]: Prasad, Animesh et al. “Versatile Layout Understanding via Conjugate Graph.” 2019 International Conference on Document Analysis and Recognition (ICDAR) (2019): 287-294.
[2] :Mirhoseini, A. et al. “Chip Placement with Deep Reinforcement Learning.” ArXiv abs/2004.10746 (2020)

Application instructions

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.

Due to the changing travel restrictions related to COVID-19, it may not be possible to host candidates from certain regions. This will depend on the conditions at the specific starting date of the internship.

About NAVER LABS

NAVER LABS Europe has full-time positions, PhD and PostDoc opportunities throughout the year which are advertised here and on international conference sites that we sponsor such as CVPR, ICCV, ICML, NeurIPS, EMNLP etc.

NAVER LABS Europe is an equal opportunity employer.

NAVER LABS are in Grenoble in the French Alps. We have a multi and interdisciplinary approach to research with scientists in machine learning, computer vision, artificial intelligence, natural language processing, ethnography and UX working together to create next generation technology and services that deeply understand users and their contexts.

Apply to this internship
Drop files here browse files ...
Drop files here browse files ...
Drop files here browse files ...
Captcha

Related Jobs

25 November 2020
Full Body 3D Human Pose in the Wild - Internship   Meylan, Grenoble, France, France
19 November 2020
16 November 2020
Learning to grasp as a human demonstration - Internship   Meylan, Grenoble, France, France
16 November 2020
5 November 2020
Are you sure you want to delete this file?
/