What Formal Languages Can Transformers Express? A Survey
Transactions of the Association for Computational Linguistics(2023)
摘要
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要