04/12/2020
The Human Resources Strategy for Researchers

Thesis offer: Computer science, NLP and machine learning (M/F)

This job offer has expired


  • ORGANISATION/COMPANY
    CNRS
  • RESEARCH FIELD
    Computer science
    Engineering
    Mathematics
  • RESEARCHER PROFILE
    First Stage Researcher (R1)
  • APPLICATION DEADLINE
    25/12/2020 23:59 - Europe/Brussels
  • LOCATION
    France › VILLEURBANNE
  • TYPE OF CONTRACT
    Temporary
  • JOB STATUS
    Full-time
  • HOURS PER WEEK
    35
  • OFFER STARTING DATE
    01/02/2021

OFFER DESCRIPTION

The thesis will be partly carried out at the LIRIS laboratory at INSA Lyon (La Doua Campus in Villeurbanne, Blaise Pascal Building) and at the ICAR laboratory at ENS Lyon.

This thesis project is part of the GEODE project ("Encyclopedic GEOgraphical DiscoursE: Writing about Geography in France from the Enlightenment to the Age of Wikipedia") funded by LabEx ASLAN for the period 2020-2024.
This interdisciplinary project brings together a consortium of researchers in computer science, linguistics, geography and history from the LIRIS, ICAR, EVS, LLF and LIDILEM laboratories and the Alan Turing Institute (London). GEODE builds on the results of previous projects in which the different partners have been able to collaborate and aims to extend its scientific objectives.

Objectives of the thesis :
The main objective is the development of methods for the study of major changes in geographical discourse in French encyclopaedias between the second half of the 18th century (Encyclopaedia of Diderot and d'Alembert) and today (Wikipedia).
The thesis work will be composed of several complementary objectives.
First of all, the doctoral student will focus on the preprocessing of the corpus (homogenisation of formats, corrections, annotations) so that the content of each encyclopaedia can be processed by automatic methods. Then, the proposal will consist in developing suitable algorithms for automatic analysis and search of geo-semantic information and discourse routines. The PhD student will be particularly interested in the development of linguistic models adapted to the diachronic analysis of geographical discourse. The methodology will be based on the design of a processing chain requiring specific resources for the processing of geo-historical data (annotated documents, linguistic models, geographical resources, etc.). This processing chain will involve supervised or semi-supervised classification methods for the classification of texts and the automatic retrieval of discourse routines as well as deep learning methods for the generation of language models (such as word embeddings). Finally, one stage of the work will also consist of proposing adapted visualisation methods for the analysis and comparison of different corpora.
One of the originalities of this thesis will be to combine quantitative and qualitative approaches in order to shed light on i) the strategies selected for the automatic classification of texts and the generation of language models ii) the interpretation of the results obtained by these methods. The main objective of this thesis will therefore be the development and improvement of automatic geographic information retrieval and search methods for the analysis of geographic discourses. Among the expected results, one can mention the availability of data, resources, results and algorithms (corpus preparation and correction, morphosyntactic annotations, geo-semantic annotations, language models, geographic resources) that will be produced during the thesis as well as the scientific valorisation of the methods developed and the results obtained.

Required profile and skills:
Master's degree or engineering school with skills in computer science, natural language processing (NLP) and corpus analysis. Knowledge of artificial intelligence (machine learning) and digital humanities will be appreciated.

Applications should include: a CV, a cover letter for the research topic concerned and grades.

More Information

Required Research Experiences

  • RESEARCH FIELD
    Engineering
  • YEARS OF RESEARCH EXPERIENCE
    None
  • RESEARCH FIELD
    Computer science
  • YEARS OF RESEARCH EXPERIENCE
    None
  • RESEARCH FIELD
    Mathematics
  • YEARS OF RESEARCH EXPERIENCE
    None

Offer Requirements

  • REQUIRED EDUCATION LEVEL
    Engineering: Master Degree or equivalent
    Computer science: Master Degree or equivalent
    Mathematics: Master Degree or equivalent
  • REQUIRED LANGUAGES
    FRENCH: Basic
Work location(s)
1 position(s) available at
Laboratoire d'Informatique en Image et Systèmes d'Information
France
VILLEURBANNE

EURAXESS offer ID: 584214
Posting organisation offer ID: 19008

Disclaimer:

The responsibility for the jobs published on this website, including the job description, lies entirely with the publishing institutions. The application is handled uniquely by the employer, who is also fully responsible for the recruitment and selection processes.

 

Please contact support@euraxess.org if you wish to download all jobs in XML.