Fetching the paper…
Reading the bibliography…
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.
On finite monoids having only trivial subgroups
Marcel Paul Schützenberger. 1965 · 1965
Earlier work this paper cites.
Counter-free Automata
R. McNaughton and S. Papert. 1971 · 1971
Earlier work this paper cites.
Parity, circuits, and the polynomial-time hierarchy
Merrick Furst, James B. Saxe, and Michael Sipser. 1984 · 1984
Earlier work this paper cites.
Finite-state transducers in language and speech processing
Mehryar Mohri. 1997 · 1997
Earlier work this paper cites.
Harmony, Dominance, and Control
Eric Bakovic. 2000 · 2000
Earlier work this paper cites.
Computational approaches to morphology and syntax
Brian Roark and Richard Sproat. 2007 · 2007
Earlier work this paper cites.
Aperiodic two-way transducers and FO-transductions
Olivier Carton and Luc Dartois. 2015 · 2015
Earlier work this paper cites.
First-order definability of rational transductions: An algebraic approach
Emmanuel Filiot, Olivier Gauwin, and Nathan Lhote. 2016 · 2016
Earlier work this paper cites.
Attention is all you need
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017 · 2017
Earlier work this paper cites.
Mikołaj Bojańczyk. 2018 · 2018
Earlier work this paper cites.
Single-use automata and transducers for infinite alphabets
Mikołaj Bojańczyk and Rafal Stefański. 2020 · 2020
Cited alongside, same era.
Theoretical limitations of self-attention in neural sequence models
Michael Hahn. 2020 · 2020
Cited alongside, same era.
Implicit automata in typed λ \lambda -calculi I: aperiodicity in a non-commutative logic
Cécilia Pradic and Lê Thành Dũng Nguyễn. 2020 · 2020
Cited alongside, same era.
Two-way transducers with planar behaviours are aperiodic
Lê Thành Dũng Nguyễn. 2021 · 2021
Cited alongside, same era.
Attention is Turing-complete
Jorge Pérez, Pablo Barceló, and Javier Marinkovic. 2021 · 2021
Cited alongside, same era.
Thinking like transformers
Gail Weiss, Yoav Goldberg, and Eran Yahav. 2021 · 2021
Cited alongside, same era.
Formal language recognition by hard attention Transformers: Perspectives from circuit complexity
Yiding Hao, Dana Angluin, and Robert Frank. 2022 · 2022
Later among the works it cites.
Saturated transformers are constant-depth threshold circuits
William Merrill, Ashish Sabharwal, and Noah A. Smith. 2022 · 2022
Later among the works it cites.
Neural networks and the Chomsky hierarchy
Grégoire Delétang, Anian Ruoss, Jordi Grau-Moya, Tim Genewein, Li Kevin Wenliang, Elliot Catt, Chris Cundy, Marcus Hutter, Shane Legg, Joel Veness, and Pedro A. Ortega. 2023 · 2023
Later among the works it cites.
Two-way automata and transducers with planar behaviours are aperiodic
Lê Thành Dũng Nguyễn, Camille Noûs, and Cécilia Pradic. 2023 · 2023
Later among the works it cites.
Challenging BIG-bench tasks and whether chain-of-thought can solve them
Mirac Suzgun, Nathan Scales, Nathanael Schärli, Sebastian Gehrmann, Yi Tay, Hyung Won Chung, Aakanksha Chowdhery, Quoc Le, Ed Chi, Denny Zhou, and Jason Wei. 2023 · 2023
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Shunyu Yao, Binghui Peng, Christos Papadimitriou, and Karthik Narasimhan. 2021 · 2021
Cited alongside, same era.
Transducers of polynomial growth
Mikołaj Bojańczyk. 2022 · 2022
Cited alongside, same era.
Overcoming a theoretical limitation of self-attention
David Chiang and Peter Cholak. 2022 · 2022
Cited alongside, same era.
Logical languages accepted by transformer encoders with hard attention
Pablo Barceló, Alexander Kozachinskiy, Anthony Widjaja Lin, and Vladimir Podolskii. 2024 · 2024
Closest in time.
The expressive power of transformers with chain of thought
William Merrill and Ashish Sabharwal. 2024 · 2024
Closest in time.
What formal languages can transformers express? A survey
Lena Strobl, William Merrill, Gail Weiss, David Chiang, and Dana Angluin. 2024 · 2024
Closest in time.
Masked hard-attention transformers recognize exactly the star-free languages
Andy Yang, David Chiang, and Dana Angluin. 2024 · 2024
Closest in time.