Julien will be giving a talk at the UCL Institute of Health Informatics about Relation extraction from biomedical literature for drug discovery.
The challenge of Drug discovery is double: it requires us to understand the biological rationale for the disease as well as finding novel biological associations which can lead to the development of a new drug. In this context, extracting biomedical interactions from the literature is key and I will give an overview of how at BenevolentAI we approach this problem. I will present "interpret", a method we recently published at ACL'19, a major NLP conference. It allows drug scientists to find literature evidence for specific types of biomedical interactions in the absence of curated datasets.
Julien Fauqueur is an AI research manager at BenevolentAI developing Natural Language Processing methods for Biomedical Information Extraction. He holds a PhD in Computer Science from INRIA (France). While a research associate at the University of Cambridge, then as a researcher in start-ups, he developed new methods and products using computer vision and machine learning. His work was published in over 20 publications and led to 4 patents.