About me

I am a postdoctoral researcher in Natural Language Processing (NLP) working with prof. Ivan Titov. My main research interests include multilingual NLP, modular deep learning, interpretability and social biases in language models.

Previously, I obtained a PhD in NLP at the University of Amsterdam (UvA) under the supervision of dr. Ekaterina Shutova and dr. Dan Garrette (Google Research). My PhD research was supported by a Google PhD fellowship. Before my PhD I graduated with a bachelor’s and master’s degree in Artifical Intelligence from the UvA and worked as a research assistant for prof. Jelle Zuidema.

Selected publications

Visit my Google Scholar Page for a full list of my publications.

The Echoes of Multilinguality: Tracing Cultural Value Shifts during LM Fine-tuning.
Rochelle Choenni, Anne Lauscher, Ekaterina Shutova.
In Proceedings of ACL 2024. [pdf]

Examining Modularity in Multilingual LMs via Language-Specialized Subnetworks.
Rochelle Choenni, Ekaterina Shutova, Dan Garrette.
In Findings of NAACL 2024. [pdf]

How do languages influence each other? Studying cross-lingual data sharing during LM fine-tuning.
Rochelle Choenni, Dan Garrette, Ekaterina Shutova.
In Proceedings of EMNLP 2023. [pdf]

Cross-lingual Transfer with Language-specific Subnetworks for Low-resource Dependency Parsing.
Rochelle Choenni, Dan Garrette, Ekaterina Shutova.
Computational Linguistics 1-37, 2023. [pdf]

Stepmothers are mean and academics are pretentious: What do pretrained language models learn about you?
Rochelle Choenni, Ekaterina Shutova, Robert van Rooij.
In Proceedings of EMNLP 2021. [pdf]

Investigating Language Relationships in Multilingual Sentence Encoders through the Lens of Linguistic Typology.
Rochelle Choenni, Ekaterina Shutova.
Computational Linguistics 48(2), 2022. [pdf]