Paris NLP saison 8 Meetup #4

Publicis Sapient, Romain Benassi, Consultant Data Scientist

Title: Extraction of medicine characteristics from official documents

Summary : Few years ago, a project to set up a Data Science platform was carried out and enabled the industrialization of NLP models for extracting information from medical texts. The point was to develop strategic services such as giving access of relevant data, searching for medicine information or securing the prescriptions. This talk will focus on the constraints and technical issues surrounding the platform, as well as the different tools constituting it and the algorithms designed. A final discussion about how the emergence of GenAI might have changed the way such a project could be handled today will be conducted as well.

---------------------

Algolia, Paul-Louis Nech, Research Machine Learning Engineer

Title: Where’s the beef? Evaluating the quality of content in your GenAI Project

**Summary: **So you created a GenAI project based on your company’s content and some LLMs. Is the generated content any good?
From eyeballing it during development to state-of-the-art user behavior tracking, there are many ways you can approach this.
In this talk, Paul-Louis will present a GenAI feature currently in Private beta at Algolia;
how they approached generating content for a diverse set of customers across the globe;
and a few techniques you can try for qualitative and quantitative assessments of your own generative projects!