📜 Research

* denotes equal contribution.

The Stanford AI Lab Blog, 2022

Faithful, interpretable model explanations via causal abstraction

Atticus Geiger, Zhengxuan Wu, Karel D'Oosterlinck, Elisa Kreiss, Noah D. Goodman, Thomas Icard, and Christopher Potts.

Preprint, 2022

Causal Proxy Models for Concept-Based Model Explanations

Zhengxuan Wu*, Karel D'Oosterlinck*, Atticus Geiger*, Amir Zur, Christopher Potts.

NeurIPS, 2022

CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior

Eldar David Abraham*, Karel D'Oosterlinck*, Amir Feder*, Yair Ori Gat*, Atticus Geiger*, Christopher Potts*, Roi Reichart*, Zhengxuan Wu*.

1st International Workshop on Automatic Translation for Signed and Spoken Languages (AT4SSL), 2021

Frozen Pretrained Transformers for Neural Sign Language Translation

Mathieu De Coster, Karel D'Oosterlinck, Marija Pizurica, Paloma Rabaey, Severine Verlinden, Mieke Van Herreweghe, Joni Dambre

MSc Thesis, 2021

Design and analysis of domain adaptation systems for joint multilingual coreference resolution

Awarded the 2021 TomTom Prize for Best Engineering Thesis

Karel D'Oosterlinck, Semere Kiros Bitew, Johannes Deleu, Thomas Demeester, Chris Develder