Publications

Retrieving Texts based on Abstract Descriptions
Linear Guardedness and its Implications
Conformal Nucleus Sampling
Analyzing Gender Representation in Multilingual Models
Adversarial Concept Erasure in Kernel Space
Linear Adversarial Concept Erasure
Measuring and Improving Consistency in Pretrained Language Models
Contrastive Explanations for Model Interpretability
Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals
It’s not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection
Ab Antiquo: Neural Proto-language Reconstruction
Can LSTM Learn to Capture Agreement? The Case of Basque
Unsupervised Distillation of Syntactic Information from Contextualized Word Representations