Yves Peirsman
Co-founder And CTO at Creatief Schrijven vzw
Leuven, Flemish Brabant, Belgium
Summary
🤩
Rockstar🎓
Top SchoolYves Peirsman is a co-founder and CTO with two decades of deep expertise in Natural Language Processing, blending academic research (KU Leuven, Stanford) with product-focused engineering at companies like Textkernel and Wolters Kluwer. He builds practical NLP systems across domains—finance, healthcare, e-commerce, publishing and mobility—currently applying AI to streamline compliance at Deontic. A prolific open-source contributor, his NLP models and educational notebooks (nlptown/nlp-notebooks) have been widely used and downloaded, with a focus on sentence similarity techniques and pretrained embeddings. Yves also founded NLP Town to help organizations operationalize state-of-the-art language models and organizes the Belgium NLP Meetup to connect practitioners. Beyond engineering, he writes fiction—multiple crime novels and a forthcoming literary novel—bringing an unusual creative perspective to language technology.
11 years of coding experience
11 years of employment as a software developer
MSc Speech & Language Processing, MSc Speech & Language Processing at The University of EdinburghMA Linguistics, MA Linguistics at KU LeuvenBroederschool Sint-Niklaas
Stackoverflow
3,089reputation
266kreached
52answers
5questions
elasticsearch
top-5%
nlp
top-1%
Github Skills (16)
scikit10
scikit-learn10
word-embeddings10
nlp10
python10
natural-language-processing10
tf-idf10
gensim9
elasticsearch9
nltk6
stanford-nlp6
language-detection6
sentiment-analysis6
spacy6
machine-learning6
Programming languages (5)
Github contributions (5)
nlptown/nlp-notebooks
Apr 2018 - May 2022
A collection of notebooks for Natural Language Processing from NLP Town
Role in this project:
Data Scientist
Data ScientistContributions:60 commits, 52 pushes, 1 branch in 4 years 1 month
Contributions summary:Yves's commits primarily focus on developing sentence similarity models within the context of NLP notebooks. The code modifications involve implementing and refining methods to determine semantic similarity between sentences using techniques such as TF-IDF weighting, word mover's distance and Smooth Inverse Frequency. The contributions also include the exploration of pretrained word embeddings, with an emphasis on their impact on model performance.
nlplanguage-processingtownmachine-learningnatural-language
nlptown/nlppapers
Jan 2018 - Aug 2018
Contributions:43 commits, 39 pushes, 1 branch in 6 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.