Hande Celikkanat

Are Multilingual Neural Machine Translation Models Better at Capturing Linguistic Features?

Jörg Tiedemann, David Mareček, Miikka Silfverberg, 2020, Prague Bull. Math. Linguistics.

Controlling the Imprint of Passivization and Negation in Contextualized Representations

Jörg Tiedemann, Marianna Apidianaki, Hande Celikkanat, 2020, BLACKBOXNLP.

On the differences between BERT and MT encoder spaces and how to address them in translation tasks

Jörg Tiedemann, Mathias Creutz, Hande Celikkanat, 2021, ACL.