From Complex to Clear: Understanding Your NLP Models

Abstract
When training and evaluating machine learning models, it is important to understand why the model made its decision the way it did. This is what explainable machine learning is all about.
By providing an understanding of modern large language models and how they work, I will explain why explainable machine learning is an essential core part of any model development and evaluation pipeline.

This workshop aims to provide practitioners with practical insights, offering a toolbox of approaches to improve their understanding of models and lift the veil on these seemingly opaque "black box" models.

Throughout the workshop, we will be using an open-source model as a working example and accessing it through the popular framework huggingface. While the common frameworks are based on Python, I will show you how to use the best of both worlds and mix and match Python code chunks with R to learn more about your model.