I am a graduate student at McGill University and Mila Quebec AI Institute, where I learn about computer science and do research under the supervision of Jackie C. K. Cheung on natural language understanding.

Ultimately, I would like to teach computers how to use language the same way we do – but that’s a long way off. In the meantime, I work on language tasks such as temporal expression recognition, lexical semantic change detection and coreference resolution.  


Martin Pömsl and Roman Lyapin (2020). CIRCE at SemEval-2020 Task 1: Ensembling Context-Free and Context-Dependent Word Representations. In Proceedings of the Fourteenth Workshop on Semantic Evaluation. Barcelona (online): International Committee for Computational Linguistics, pp. 180–186. Code.


Pömsl, Martin (2021). Extending Neural Temporal Tagging Systems with External Knowledge. Bachelor Thesis. Osnabrück University.