I am an assistant professor (maître de conférences, HDR) in computer science, specialised in computational linguistics/natural language processing. I am affiliated to Aix Marseille University in France, and member of the TALEP research group of LIS. I am a member of the gender equality commission of LIS and one of the organisers of les Cigales, a maths camp for highschool girls. I co-authored with Marion Cluzel the comic strip "La grande aventure du TAL".
I am passionate about multiword expressions (MWEs) and I work on building NLP systems that take them into account. I am the main author of the mwetoolkit software, and also wrote a book on MWEs available on Springer Link. (errata). I am also interested in parsing, semantics, representations, annotation, low-resourced languages, unsupervised and semi-supervised methods, and (of course) language models.
I am involved in the PARSEME community, especially in the organisation of the shared tasks in 2017, 2018 and 2020, on verbal MWE identification. I also gave a course on MWEs at ESSLLI 2018, a tutorial on MWEs at LREC 2022, and a course on scientific methodology at ESSLLI 2024. I obtained my PhD in 2012 from the University of Grenoble (France) and the Federal University of Rio Grande do Sul (Brazil) under the supervision of C. Boitet and Aline Villavicencio. I have a Bachelor's degree from the Federal University of Rio Grande do Sul and a Master's degree from ENSIMAG at Grenoble INP. I was co-chair of the 2010, 2011, 2013, 2017, 2018, 2020, 2021 and 2022 editions of the workshop on multiword expressions, as well as area chair of several conferences. I was the elected representative of the MWE Section of SIGLEX from 2020 to 2022. I am a member of the editorial board of LSP's series on Phraseology and Multiword Expressions (PMWE).
I defended my habilitation à diriger des recherches (HDR) in 2023 at Aix Marseille University, entitled Multiword expressions in computational linguistics:
You can find my email address on the first page of most of my publications.
I also have a gmail address, with the same username.
LIS-TALEP Parc Scientifique et Technologique de Luminy 163, avenue de Luminy - Case 901 13288 MARSEILLE CEDEX 9 France