no code implementations • 2 Apr 2024 • Lena Strobl, Dana Angluin, David Chiang, Jonathan Rawski, Ashish Sabharwal
We study the sequence-to-sequence mapping capacity of transformers by relating them to finite transducers, and find that they can express surprisingly large classes of transductions.
1 code implementation • COLING 2022 • Josef Valvoda, Naomi Saphra, Jonathan Rawski, Adina Williams, Ryan Cotterell
Recombining known primitive concepts into larger novel combinations is a quintessentially human cognitive capability.
no code implementations • WS 2019 • Jane Chandlee, Remi Eyraud, Jeffrey Heinz, Adam Jardine, Jonathan Rawski
This paper examines the characterization and learning of grammars defined with enriched representational models.