Papers accepted at CoNLL 2024 and NeurIPS 2024

We are happy to announce that four papers by members of our department have been accepted at the  SIGNLL Conference on Computational Natural Language Learning (CoNLL) 2024 and the Conference on Neural Information Processing Systems (NeurIPS) 2024.
Congratulations to all authors, especially to our Master students Yash Sarrof and Yana Veitsmann!

CoNLL:

• “Lossy Context Surprisal Predicts Task-Dependent Patterns in Relative Clause Processing” by Kate McCurdy and Michael Hahn.

NeurIPS: 

• “Separations in the Representational Capabilities of Transformers and Recurrent Architectures.” by Satwik Bhattamishra, Michael Hahn, Phil Blunsom and Varun Kanade.
• “InversionView: A General-Purpose Method for Reading Information from Neural Activations.” by Xinting Huang, Madhur Panwar, Navin Goyal and Michael Hahn.
• “The Expressive Capacity of State Space Models: A Formal Language Perspective.” by Yash Sarrof, Yana Veitsman and Michael Hahn.