all AI news
What Formal Languages Can Transformers Express? A Survey
May 8, 2024, 4:43 a.m. | Lena Strobl, William Merrill, Gail Weiss, David Chiang, Dana Angluin
cs.LG updates on arXiv.org arxiv.org
Abstract: 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 …
abstract arxiv capabilities computation cs.cl cs.fl cs.lg cs.lo express fundamental language language processing languages natural natural language natural language processing power processing questions researchers solve survey transformers type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US