About me
NLP for endangered and underrepresented languages
I am a postdoctoral researcher in Natural Language Processing working with Alexander Fraser at the Technische Universität München (TUM) Campus Heilbronn. My work focuses on parallel sentence mining for low-resource languages.
Previously, I was a PhD student at the Université Paris-Saclay (LISN/CNRS laboratory, formerly known as LIMSI) under the supervision of François Yvon. My thesis topic was Computational Language Documentation.
My research interests revolve around building models and tools for endangered and underrepresented languages by leveraging available resources.
Research topic keywords: computational language documentation, word and morpheme segmentation, interlinear glossing, parallel sentence mining, multilingual representation, machine translation, NLP for endangered languages, low-resource NLP.
Milestones
- 1 May 2024: Started as a postdoctoral researcher at TUM Heilbronn in Alexander Fraser’s team.
- 19 December 2023: Defended my PhD thesis (in French).
News
More regular updates on Bluesky (from September 2026).
- 15 September 2026: Presented Low-Resource Morphological Inflection for Kashubian at KONVENS 2026 in Hamburg, Germany.
- 2 July 2026: Presented Vers une fouille de phrases parallèles pour les langues régionales de France métropolitaine (in French; Towards the Parallel Sentence Mining for Regional Languages of Metropolitan France) at TALN 2026 in Nantes, France.
- 16 May 2026: Presented our tutorial Low-Resource, High-Impact: Building Corpora for Inclusive Language Technologies at LREC 2026 in Palma, Spain.
- 16 April 2026: Presented NLP Models for Field Linguistic Annotations in Computational Language Documentation at the monthly online ILFC Seminar.
Contact
first_name [dot] last_name [at] tum [dot] de
How to pronounce my name.