With this new AI Lab, we aim to fill the gap in Biomedical and Clinical NLP for European languages

After graduating from my Doctoral degree at UGent, I had the immense privilege of  being accepted in an NVIDIA internship program in collaboration with ORSI, the leading academy of Robotics-Assisted Surgery in Europe.

This six-month internship culminated in the public demonstration of a Vision-and-Language model commenting an ongoing surgery live during the Surgical AI days, a world-first!

Join me on Thursday 30th May 2024 at 2 PM for the public defense of my doctoral thesis, on which I worked during the last five years and is titled…

You can find recent Biomedical NLP papers on my dedicated Mastodon account and now also in my brand new HuggingFace collection. Keep reading for more details!

This Monday (2021-07-12) marked the official start of the ADAM project, a collaboration between AZ Delta’s RADAR team and our own Internet and Data science Lab (IDLab, joint venture of UGent & imec).

Given I will be lead researcher on the Natural Language Understanding aspect of this project, I wanted to talk about it on my blog as well. Our shared goal in the ADAM project is to enable personalized medicine through deep patient understanding, which requires natural language processing of Dutch clinical notes.

In this technical report, the training procedure of our Transformer-based Dutch-to-English translation model will be outlined. This model was trained exclusively using freely available datasets, and yet achieves a performance level superior to the current state of the art in the domain.

We show this by comparing the precision and recall of MetaMap’s medical concepts extraction when executed on a set of Dutch clinical notes after translation to English, as well as by using more conventional quality metrics for translation models (BLEU…).