En poursuivant votre navigation sur ce site, vous acceptez le dépôt de cookies dans votre navigateur. (En savoir plus)
Portail > Offres > Offre UMR5505-CHLBOU-065 - CDD chercheur (H/F) en fouille de données textuelles et visualisation de données

Postdoctoral position in text-mining and data visualisation

This offer is available in the following languages:
Français - Anglais

Date Limite Candidature : mercredi 1 février 2023

Assurez-vous que votre profil candidat soit correctement renseigné avant de postuler. Les informations de votre profil complètent celles associées à chaque candidature. Afin d’augmenter votre visibilité sur notre Portail Emploi et ainsi permettre aux recruteurs de consulter votre profil candidat, vous avez la possibilité de déposer votre CV dans notre CVThèque en un clic !

General information

Reference : UMR5505-CHLBOU-065
Nombre de Postes : 1
Workplace : TOULOUSE
Date of publication : Wednesday, January 11, 2023
Type of Contract : FTC Scientist
Contract Period : 15 months
Expected date of employment : 1 March 2023
Proportion of work : Full time
Remuneration : From 2805 to 3963 euros gross monthly according to experience
Desired level of education : PhD
Experience required : Indifferent

Missions

Development of a range of data mining algorithms for the interactive exploration of a corpus of digitised texts relating to 16th century inquisition trials.

Activities

The D4R project (Religious Dissent and Reception of the Reformation in Renaissance Spain (16th c.) More details at https://d4r.hypotheses.org/) is a multidisciplinary digital humanities project that aims to design a software platform that allows historians to explore a corpus of documents to assist them in their analytical work. The data corpus consists of a large volume of historical texts and inquisition trials in Spanish, digitised in an XML TEI format. The objective of the platform is to use relevant visual representations (knowledge graphs, etc.) and intuitive user interactions to facilitate natural navigation through the content of the documents, i.e. people, places, events or theological concepts. The originality of the platform is the integration of an algorithm driven by the user in an interactive way, in order to assist the latter in highlighting relevant information.
The project team consists of researchers in History, Linguistics and Computer Science, as well as a doctoral student in digital humanities. The project also includes an international collaboration dimension with Spain (Barcelona, Madrid, Toledo, Bilbao). The development of the platform will be entrusted to a web development engineer who will be recruited for the project. However, the algorithm(s) that govern its internal functioning will have to be developed specifically within this postdoctoral contract.

Skills

- Proven skills in data mining and text analysis are essential for the successful completion of the task. Additional experience in machine learning (word-embedding, etc.) may be useful in the development of certain features.
- Ideally, the candidate will have skills or experience in computer science (Python, etc.) or computational linguistics.
- Experience in project management and git will be appreciated in the context of the collaboration with the person in charge of developing the platform.
- Finally, knowledge of the Spanish language will be appreciated given the context of the work.

Work Context

The successful candidate will be hosted at the Institut de Recherche en Informatique de Toulouse on the Paul Sabatier University site. He/she will benefit from the supervision of Prof. Josiane Mothe and Dr. David Panzoli, as well as the environment provided by the other researchers, PhD students and postdoctoral fellows of the laboratory.

We talk about it on Twitter!