Formal Language Recognition by Hard Attention Transformers: Perspectives from Circuit Complexity
Top Cited Papers
Open Access
- 27 July 2022
- journal article
- research article
- Published by MIT Press in Transactions of the Association for Computational Linguistics
- Vol. 10, 800-810
Abstract
This paper analyzes three formal models of Transformer encoders that differ in the form of their self-attention mechanism: unique hard attention (UHAT); generalized unique hard attention (GUHAT), which generalizes UHAT; and averaging hard attention (AHAT). We show that UHAT and GUHAT Transformers, viewed as string acceptors, can only recognize formal languages in the complexity class AC0, the class of languages recognizable by families of Boolean circuits of constant depth and polynomial size. This upper bound subsumes Hahn’s (2020) results that GUHAT cannot recognize the DYCK languages or the PARITY language, since those languages are outside AC0 (Furst et al., 1984). In contrast, the non-AC0 languages MAJORITY and DYCK-1 are recognizable by AHAT networks, implying that AHAT can recognize languages that UHAT and GUHAT cannot.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Self-Attention Networks Can Process Bounded Hierarchical Languages2021
- Theoretical Limitations of Self-Attention in Neural Sequence ModelsTransactions of the Association for Computational Linguistics, 2020
- On the Ability and Limitations of Transformers to Recognize Formal Languages2020
- Effective Approaches to Attention-based Neural Machine Translation2015
- Computational Complexity2009
- Parity, circuits, and the polynomial-time hierarchyTheory of Computing Systems, 1984