Some adblockers block the registration window. If you do not see the registration box below, please check your adblocker settings.

General Information

The eScience Center offers a range of workshops and training courses, aimed at PhD candidates and other researchers or research software engineers. We organize workshops covering digital skills needed to put reproducible research into practice. These include online collaboration, reproducible code and good programming practices. We also offer more advanced workshops such as GPU Programming, Parallel Programming, Image Processing and Deep Learning.

This lesson teaches the fundamentals of Natural Language Processing (NLP) in Python. It will equip you with the foundational skills and knowledge needed to carry over text-based research projects. The lesson is designed with researchers in the Humanities and Social Sciences in mind, but is also applicable to other fields of research.

On the first day we will dive into the importance of linguistic principles when dealing with text data, we will also teach basic techniques for text preprocessing and understand the principles behind word embeddings. The second day begins with an introduction to transformers, followed by hands-on work on classification tasks with the BERT model including basic evaluation techniques. In the afternoon, we will cover large language language models, learn to work locally with open source models and understand potential drwbacks and biases when using this technology.

Where: Science Park 402, 1098 XH Amsterdam. Get directions with OpenStreetMap or Google Maps.

When: May 26 - 27, 2026, 9:30 - 17:00 CEST.

Requirements: Participants must bring a laptop with a Mac, Linux, or Windows operating system (not a tablet, Chromebook, etc.) that they have administrative privileges on. They should have a few specific software packages installed (listed below).

Accessibility: We are committed to making this workshop accessible to everybody. The workshop organizers have checked that:

• The room is wheelchair / scooter accessible.
• Accessible restrooms are available.

Materials will be provided in advance of the workshop and large-print handouts are available if needed by notifying the organizers in advance. If we can help making learning easier for you (e.g. sign-language interpreters, lactation facilities) please get in touch (using contact details below) and we will attempt to provide them.

Workshop files: You will find all slides, notebooks, archived collaborative documents, and other relevant files in the files folder of the workshop website repository after the workshop.

Contact: Please email or training@esciencecenter.nl for more information.

---

Code of Conduct

Participants are expected to follow these guidelines:

• Use welcoming and inclusive language
• Be respectful of different viewpoints and experiences
• Gracefully accept constructive criticism
• Focus on what is best for the community
• Show courtesy and respect towards other community members

Syllabus

Introduction

• What is Natural Language Processing (NLP)?
• Why learn NLP fundamentals?
• NLP applications and the relationship to LLMs
• Extracting text properties with spaCy

A Primer on Linguistics

• NLP tasks taxonomy
• What is Language Modeling?
• Why is automatic language processing difficult?
• Compositionality, ambiguity, sparsity, and discreteness

From Words to Vectors

• Preprocessing operations and NLP pipelines
• From rule-based approaches to distributional semantics
• Word embeddings and Word2Vec
• Limitations of static word representations
• Training your own Word2Vec model
• Topic Modelling with BERTopic

Transformers: BERT and Beyond

• Drawbacks of static word embeddings
• The Transformer architecture
• Introduction to BERT and contextualised representations
• Using BERT for text classification
• Evaluating NLP classifiers

Large Language Models

• How LLMs differ from vanilla Transformers
• Open-source vs. proprietary models
• Choosing the right LLM for your task
• Running LLMs locally with HuggingFace and Ollama
• Prompting for classification tasks
• Biases, hallucinations, and limitations of LLMs

Schedule

All times in the schedule are in the CET timezone.

---

Setup

To participate in this workshop, you will need access to software as described below. In addition, you will need an up-to-date web browser.

We maintain a list of common issues that occur during installation as a reference for instructors that may be useful on the Configuration Problems and Solutions wiki page.

Software setup

Please follow these setup instructions in preparation for the workshop. This page includes the data sets to be downloaded as well.