Postdoctoral position in Natural Language Processing: Text Simplification
Project description

The goal of the ALECTOR project
(https://alectorsite.wordpress.com/english-overview/) is to develop
and test resources that make it possible to propose simplified texts
for children who face major problems in reading and understanding
written texts.

Job description

The successful candidate will develop methods for text simplification,
which will be applied to French, with a focus on children with
dyslexia.

The work will be built on existing simplification systems, which will
be used for comparison, such as LEXenstein, which is specific for
lexical simplification, or the methods described in (Zhang and Lapata,
2017), (Nisioi et al., 2017) or (Stajner et al., 2017).

Evaluation will be both automatic, by using MT metrics on existing
corpora, and manual, in order to focus on specific issues.

Tests will be made with existing English datasets and tools, but will
also be applied to French.

The appointed researcher will work in close collaboration with all
teams involved in the ALECTOR project.

Requirements and qualifications

    Ph.D. in Computer Science with a focus on Machine Learning or
    Natural Language Processing

    Experience in text simplification, machine translation or
    summarization would be an asset

    Experience with deep learning tools

    Good publication record

    Ability to work in a collaborative environment, with a strong
    commitment to achieving research goals

    Fluent French and/or English, strong oral and written
    communication skills

    Solid programming skills

Additional information

    Application deadline: open until filled
    Starting date: September to December 2018
    Duration: 1 year, renewable depending on performance

Applications

Applications should include the following:

    Cover letter outlining interest in the position and academic goals
    CV including a list of publications

    Recommendation letters or names and contact information of at
    least two referees

and be sent to Anne-Laure Ligozat (annlor[@]limsi.fr)