What Formal Languages Can Transformers Express? A Survey
Transactions of the Association for Computational Linguistics · 07.05.2024 · 12 · 543-561
DOI: 10.1162/tacl_a_00663 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 07.05.2024. Verfasst von Lena Strobl und 4 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 89 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
As transformers have gained prominence in natural language processing, some researchers have investigated theoretically what problems they can and cannot solve, by treating problems as formal languages. Exploring such questions can help clarify the power of transformers relative to other models of computation, their fundamental capabilities and limits, and the impact of architectural choices. Work in this subarea has made considerable progress in recent years. Here, we undertake a comprehensive survey of this work, documenting the diverse assumptions that underlie different results and providing a unified framework for harmonizing seemingly contradictory findings.
Zitieren
APA
Strobl, L., Merrill, W., Weiss, G., Chiang, D., & Angluin, D. (2024). What Formal Languages Can Transformers Express? A Survey. Transactions of the Association for Computational Linguistics, 12, 543-561. https://doi.org/10.1162/tacl_a_00663
Vancouver
Strobl L, Merrill W, Weiss G, Chiang D, Angluin D. What Formal Languages Can Transformers Express? A Survey. Transactions of the Association for Computational Linguistics. 2024;12:543-561. doi:10.1162/tacl_a_00663
BibTeX
@article{Strobl2024,
author = {Strobl, Lena and Merrill, William and Weiss, Gail and Chiang, David and Angluin, Dana},
title = {What Formal Languages Can Transformers Express? A Survey},
journal = {Transactions of the Association for Computational Linguistics},
year = {2024},
volume = {12},
pages = {543--561},
doi = {10.1162/tacl_a_00663}
}
EUVIMED