Verna Dankers
banner
vernadankers.bsky.social
Verna Dankers
@vernadankers.bsky.social
Postdoc at ‪Mila & McGill University 🇨🇦 with a PhD in NLP from the University of Edinburgh 🏴󠁧󠁢󠁳󠁣󠁴󠁿 memorization vs generalization x (non-)compositionality. she/her 👩‍💻 🇳🇱
Full house at BlackboxNLP at #EMNLP2025!! Getting ready for my 1.45PM keynote 😎 Join us in A102 to learn about "Memorization: myth or mystery?"
November 9, 2025 at 3:05 AM
Proud to accept a 5y outstanding paper award
@ijcai.org 🏆 from the Journal of AI Research for the impact Compositionality Decomposed has had, on behalf of the team (Dieuwke Hupkes, Elia Bruni & Mathijs Mul)!🧡 Come to room 513 on Wed@11.30 to learn about rethinking compgen evaluation in the LLM era🤖
August 19, 2025 at 6:28 PM
Had a blast at #ACL2025 connecting with new/familiar faces, explaining the many affiliations on my badge, chatting about memorisation--generalisation, and visiting stunning Schönbrunn. A shoutout to the co-organisers & speakers of the successful @l2m2workshop.bsky.social 🧡 I learnt a lot from you!
August 4, 2025 at 2:36 AM
Students showed increases in verbatim memorization, large increases in extractive memorization, and also hallucinated much more than baselines! We go beyond average-case performance through additional analyses of how T, B, and S perform on data subgroups... (3/5)
July 27, 2025 at 3:37 PM
SeqKD is still widely applied in NMT to obtain strong & small deployable systems, but your student models do not only inherit good things from teachers. In our short paper, we contrast baselines trained on the original corpus to students (trained on teacher-generated targets). (2/5)
July 27, 2025 at 3:37 PM
Thrilled to be in Vienna to learn about all the papers & catch up with NLP friends 🇦🇹 You'll find me at the ACL mentorship session (Mon 2PM), at our @l2m2workshop.bsky.social (Fri) and at my poster (Wed 11AM)! I'll present work w/ @vyraun.bsky.social on memorization in NMT under SeqKD #ACL2025 (1/5)
July 27, 2025 at 3:37 PM