Extreme Multilabel Classification in the Biomedical NLP Domain

This talk is based on a project I did for the Wellcome Trust for which I had to develop a model that assigns the most relevant of 29K MeSH tags. If you want to read more about this topic, here are some additional blogs I have written A neural network tagging biomedical grants Tagging biomedical grants with 29K tags Making an optimisation algorithm 10K times faster

June 8, 2022 · 1 min

To explain or to predict?

This talk is about an interesting topic I started reading about at the start of my career as a data scientist. In particular about the differences between using machine learning techniques for prediction vs more explanatory techniques, commonly used in sciences like regression.

May 7, 2017 · 1 min

Making recommendations without data

This talk is based on my work while at 6 tribes which was a new social network with the goal of connecting you with like minded people. As such at its core the product relied on recommendations but at the same time there were no or limited user data to base those recommendations.

May 8, 2016 · 1 min