Starting period: Autumn 2023
Duration: 12-month postdoctoral contract, renewable)
Location: Sorbonne University (ISIR lab in the MLIA team) / DataLab of the BNF

Supervision:
– Laure Soulier, MCF in computer science at Sorbonne University, MLIA team, ISIR.
– Vincent Guigue, Professor in computer science at AgroParisTech.
– Lucie Termignon,  data and artificial intelligence project manager at the BnF.
– Jean-Philippe Moreux, Scientific expert of Gallica at the BnF.

This project consists of working on access to information in the Gallica library, from the point of view of machine and deep learning techniques. The research axes concern (1) the analysis and indexing of textual documents as well as (2) the analysis of user traces and (3) recommendation systems. We will focus in particular on multimodal techniques that allow to contextualize a document or a request from user interactions.

The successful candidate will be responsible for:

• Implement models to learn the semantics of textual data in order to vectorize them.
  
• Develop algorithms based on representation learning methodologies to effectively mix text and user traces.
  
• Use a large language model to generate relevant questions for the user.
  
• Report and present development work in a clear and effective way, both to discuss with BnF experts and to write machine learning publications.

More info: https://scai.sorbonne-universite.fr/public/news/view/939918bf1732e015766d/2