
Academic lab · Amsterdam, Netherlands
CLTLVU Amsterdam
VU Amsterdam's Computational Linguistics and Text Mining Lab, publishing open Dutch language resources, MedRoBERTa.nl and teaching material.
Amsterdam, Netherlands
- Type
- Academic lab
- Based in
- Amsterdam, Netherlands
- Featured projects
- 7
About
The Computational Linguistics and Text Mining Lab at Vrije Universiteit Amsterdam is led by Piek Vossen and Antske Fokkens. It has moved from computational lexicology and terminology toward broader work in AI and computational linguistics, with research themes in identity, reference and perspectives, meaning representation, and large language models and interpretability.
Vossen founded the Global WordNet Association in 2000 and presided over it until 2024, and the lab contributes to the Dutch Global Wordnet Grid. It states that it publishes models, software and resources as open source, and also teaches a Language and AI master's program.
MedRoBERTa.nl, introduced in 2021 by Stella Verkijk and Vossen, was pre-trained on nearly 10 million hospital notes from Amsterdam UMC. The lab's Python for Text Analysis course, created in 2016, has over 450 GitHub stars.
Mission and ambitionsThe lab combines computational linguistics and text mining and releases its models, software and teaching resources openly.
Known for
- 01
MedRoBERTa.nl clinical Dutch model
- 02
Dutch wordnet work
- 03
Python for text analysis course
- 04
Open lab software
Milestones
- 2000
Global WordNet Association
Vossen founded the association that coordinates wordnets across languages.
- 2016
Python for Text Analysis
The open teaching course repository was created.
- 2021
MedRoBERTa.nl
Released a Dutch clinical language model trained on hospital notes.
- 2025
Medical model paper
An Artificial Intelligence in Medicine article described the model's development and anonymization.
Open source
If you want to use Python for text analysis, this course is for you! (457 stars)
This repo provides a python module to work with Open Dutch WordNet. It was created using python 3.4. (70 stars)
VU-CLTL Pepper/Nao Application Repository (Python 2) (31 stars)
Open-source repository. (25 stars)
- CLTL/MedRoBERTa.nlmodel
Model with 15 likes on the Hub.
- CLTL/icf-domainsmodel
Model with 1 likes on the Hub.
Space with 0 likes on the Hub.
Notable releases
Openness
Courses, tools, datasets and models are public on GitHub and Hugging Face.
People
- Piek VossenProfessor of Computational Lexicology; lab founder and head
Spinoza laureate (2013); founder of the Global WordNet Association.
- Antske FokkensProfessor and co-lead of the lab
- Stella VerkijkMedRoBERTa.nl author
- Lea KrauseMember of the cltl GitHub organization
- Stefan SchoutenMember of the cltl GitHub organization
Listed from the lab's own pages and public profiles.
Contact and community
Contact via site.
Sources
Compiled from the lab's public pages, Hugging Face and GitHub. Last checked 2026-11-17. Something wrong or out of date? Tell us on Discord.



