I'm Timothee Mickus, a postdoc at the University of Helsinki; I was involved in the ERC-funded FoTran project and the Uncertainty-aware neural language model funded by the Academy of Finland, and led by Jörg Tiedemann. I am currently part of the GreenNLP and CorCoDial projects.

I did my PhD at ATILF, under the supervision of Mathieu Constant and Denis Paperno at Utrecht University. You can read the monograph here. My PhD research topic was on distributional semantics and dictionaries: Do dictionary definitions depict meaning in the same way as neural networks-based word vectors? Can we come up with quantitative ways of measuring how similar these two theories are? This PhD was funded by the OLKi project. It received an award from the ATALA, the French scientific society for NLP.

I also hold a Masters in Computational Linguistics from the now-Université de Paris Computational Linguistics curriculum. My thesis was on distributional effects of grammatical gender contrasts on French human nouns, which you can read here.

I am actually looking for a job in academia. Don't hesitate to reach out if you have suggestions for me!

Our Mu-SHROOM shared task on hallucination detection just wrapped up! Thanks a lot to all the participants who contributed, and looking forward to the presentation at SemEval 2025. Don't hesitate to say hi if you meet me at ACL! On the same topic, I am co-organizing a workshop (collocated with AACL) on LLM hallucinations in mission-critical and multilingual scenarios. The workshop is called CHOMPS, have a look and consider submitting your work over there!

I will also be at IWCS 2025 in Düsseldorf: I'm organizing BriGap-2, a workshop on building bridges between (formal) linguistics and NLP. We got a fairly high number of submissions, thanks to all the authors who submitted their work! Keep an eye out for the program.

Below are some of the projects I've been working on or have previously worked on. (Incidentally, it's also a gallery of all the random puns & logos I came up with.)