Local attention strictly enlarges the class of regular languages recognizable by fixed-precision transformers by introducing a second temporal operator in LTL, with global and local attention being expressively complementary.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
An algorithm classifies visibly pushdown languages as AC^0, ACC^0-hard, or constant-depth equivalent to unions of newly defined intermediate VPLs.
citing papers explorer
-
Characterizing the Expressivity of Local Attention in Transformers
Local attention strictly enlarges the class of regular languages recognizable by fixed-precision transformers by introducing a second temporal operator in LTL, with global and local attention being expressively complementary.
-
The $\mathsf{AC}^0$-Complexity Of Visibly Pushdown Languages
An algorithm classifies visibly pushdown languages as AC^0, ACC^0-hard, or constant-depth equivalent to unions of newly defined intermediate VPLs.