NLP Meetup: Designing NLP for Production Systems at ML6

On the 3rd of December we had the pleasure to host the 12th edition of the Natural Language Processing (NLP) Meetup here at ML6, in Ghent.

A crowd of about 80 NLP enthusiasts were there to follow three technical talks. The first of which was co-presented by Anna Krogager and myself, Thomas Vrancken. We tackled the complexity of putting NLP applications to production, all based on our own experience of developing a large scale recommender system. It included insights on how we managed to update our live models without any downtime, using Kubeflow Pipeline. More details can be found in the slides below:

Designing real-world NLP for production systems.pdf

The two following talks were about:

• Embedding Rare Words: how (not) to get the most out of sparse data
  (by Jeroen Van Hautte, TechWolf)
• Information Extraction from Medical Notes for Early Birth Risk Prediction
  (by Lucas Sterckx, UGent-imec)

Join the below meetup page for more information about the next NLP meetups. See you guys there!

https://www.meetup.com/fr-FR/Belgium-NLP-Meetup/?_locale=fr-FR