Damien Sileo
Researcher - NLP Reasoning at Inria
Lille, Hauts-de-France
Summary
👤
Senior🎓
Top SchoolDamien Sileo is a researcher and NLP specialist with 11 years of experience combining deep learning, discourse analysis and reasoning, currently pursuing research on LLMs, logic and multi-task learning at Inria. He completed a PhD focused on sentence representation and pragmatics, with a NAACL2019 paper on mining discourse markers and a track record of top rankings in shared tasks (CAP2017, DEFT2018). His work bridges academic rigor and practical engineering—contributing to NL-Augmenter by implementing discourse marker augmentation—and spans multimodality and cognitive-science-informed approaches from a postdoc at KU Leuven to industry data science roles. Trained as an engineer at Centrale Paris with an MSc in Machine Learning, he combines theoretical insight with hands-on contributions to open-source NLP tooling and dataset design.
11 years of coding experience
3 years of employment as a software developer
Diplôme d'ingénieur, Computer science, Diplôme d'ingénieur, Computer science at Centrale Paris (Université Paris Saclay)MSc, Machine Learning, MSc, Machine Learning at Paris Sorbonne UniversitéPh.D., Natural Language Processing, Ph.D., Natural Language Processing at University of Toulouse
French, English, German, Spanish
Github Skills (6)
transformers10
text-generation10
nlp10
python10
natural-language-processing10
data-augmentation9
Programming languages (4)
Github contributions (5)
GEM-benchmark/NL-Augmenter
Jun 2021 - Jul 2021
NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations
Role in this project:
ML Engineer
ML EngineerContributions:2 reviews, 7 commits, 1 PR in 21 days
Contributions summary:Damien contributed to the `nl-augmenter` repository by implementing a discourse marker substitution transformation for natural language augmentation. Their work involved defining and refactoring the `CLASS_TO_MARKERS` dictionary, modifying code to split words, and adding a transformation function. They made multiple commits, iteratively improving and refining the code for this specific natural language processing task. The user also fixed a typo and updated the test.
nlpinformation-theorysentencedeep-learningmachine-learning
sileod/tasksource
Dec 2022 - Mar 2023
Contributions:45 releases, 133 commits, 186 pushes in 3 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.