This tutorial, organised by the University of Glasgow's AI4BioMed lab, will provide a hands-on introduction to the core tasks in biomedical natural language processing (BioNLP) for extracting knowledge from text. These include named entity recognition to identify mentions of important concepts, entity linking to connect mentions with ontologies and relation extraction methods to understand what text is saying about the entities. It will also explore the strengths and weaknesses of large language models for information extraction.

The hands-on sections are mostly easily run through Google Colab which requires a Google account for saving your edits.

Tutorial Schedule – July 15, 2025

Time Title Resources
09:00-09:15 Introduction to Biomedical Natural Language Processing View Slides
09:15-09:30 Talk: Getting started with NLP View Slides
09:30-10:00 Hands-on: Getting started with NLP Launch Notebook
10:00-10:15 Talk: Identifying mentions of biomedical concepts using named entity recognition (NER) View Slides
10:15-10:45 Hands-on: Extracting entities from text Launch Notebook
10:45-11:00 Coffee Break
11:00-11:15 Talk: Extracting relations from biomedical text View Slides
11:15-12:00 Hands-On: Relation extraction with co-occurrences and HuggingFace Launch Notebook
12:00-12:15 Talk: Using Large Language Models for biomedical text mining View Slides
12:15-12:45 Hands-On: Large language models for information extraction Launch Notebook
12:45-13:00 Talk: LLMs and the future of information extraction View Slides