En poursuivant votre navigation sur ce site, vous acceptez le dépôt de cookies dans votre navigateur. (En savoir plus)
Portail > Offres > Offre UMR5189-AURBER-004 - Chercheur CDD (Postdoc) (H/F) – Conception et développement d’un outil de deep learning pour la détection de citations en langues anciennes

Temporary Researcher (Postdoc) (M/F) - Design and development of a deep learning tool for text reuse detection in ancient languages

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

Date Limite Candidature : mercredi 4 juin 2025 23:59:00 heure de Paris

Assurez-vous que votre profil candidat soit correctement renseigné avant de postuler

Informations générales

Intitulé de l'offre : Temporary Researcher (Postdoc) (M/F) - Design and development of a deep learning tool for text reuse detection in ancient languages (H/F)
Référence : UMR5189-AURBER-004
Nombre de Postes : 1
Lieu de travail : LYON 02
Date de publication : mercredi 14 mai 2025
Type de contrat : Chercheur en contrat CDD
Durée du contrat : 12 mois
Date d'embauche prévue : 1 septembre 2025
Quotité de travail : Complet
Rémunération : Starting at €3,021 gross per month, depending on experience
Niveau d'études souhaité : Doctorat
Expérience souhaitée : Indifférent
Section(s) CN : 06 - Sciences de l'information : fondements de l'informatique, calculs, algorithmes, représentations, exploitations

Missions

As part of the BiblIndex project, an online index of biblical quotations in ancient and medieval Christian literature developed by the HiSoMA laboratory (UMR 5189) in Lyon, this postdoctoral position aims to develop innovative and generic tools for detecting textual reuse in ancient languages. The position is funded by Equipex+ Biblissima+, Observatoire des cultures écrites anciennes, de l'argile à l'imprimé (Observatory of ancient written cultures, from clay to print), of which HiSoMA is a member.
The first application corpus will consist of ancient versions of biblical texts. The aim will be to enable the identification and linking of passages within the biblical corpus itself, based on their morphosyntactic and semantic similarities, and to classify textual reuse using a detailed typology. In a second phase, the detection tool will be applied to corpora of ancient texts quoting the Bible.
In addition to the now standard procedures for preparing corpora for intertextuality detection (tokenisation, lemmatisation, n-gram segmentation, lexical embedding), the postdoc will use machine learning (supervised and unsupervised) for text data processing. This processing will involve the training of neural networks adapted to this type of task (LSTM, GRU, Transformers, etc.) on text corpora prepared by the laboratory's team of researchers specialising in ancient languages.

Activités

- Development of tools for intertextuality detection
- Iterative work in collaboration with philologists specialising in biblical and patristic texts in ancient languages.
- Integration of the tools developed into the processing chain of the BiblIndex project, in collaboration with the engineer in charge.
- Writing articles for humanities and computer science journals, alone or in collaboration.

Compétences

- Knowledge of programming languages (Python, etc.) and data analysis libraries (e.g. Pandas, Scikit-learn, etc. in Python).
- Deep learning and natural language processing skills
- Knowledge of ancient Greek and/or Latin, if possible
- Interest in or training in biblical studies
- Interest in or experience of applying computer science to the humanities
- Good interpersonal and communication skills (oral and written)
- Independence, vision and creativity.

Contexte de travail

You will work closely with Laurence Mellerin (BiblIndex programme coordinator) and will be required to interact regularly with other team members. You will be welcomed into the Sources Chrétiennes team (HiSoMA, Lyon 2e), made up mainly of researchers and engineers specialised in the study of the texts of the Church Fathers. You will have the opportunity to interact with other IT specialists involved in the work of the Biblissima+ network, in particular within Cluster 7 - Interoperability and Textual Analysis.
You will be expected to travel in France and abroad to promote the results of your research and to exchange ideas with other members of the Biblissima+ Equipex.
What we offer:
- A stimulating working environment in contact with researchers
- 44 days of leave/RTT per year
- Excellent working conditions (flexible hours, teleworking, quiet office)
- Partial reimbursement of transport costs (75%) + sustainable mobility allowance of up to €300/year
- A location accessible by public transport

Contraintes et risques

The host team is a humanities team, not an IT team, so an appetite for interdisciplinarity is essential.