On Efficiently Representing Regular Languages as RNNs

Anej Svete, Robin Chan, Ryan Cotterell


Abstract
Recent work by Hewitt et al. (2020) provides an interpretation of the empirical success of recurrent neural networks (RNNs) as language models (LMs). It shows that RNNs can efficiently represent bounded hierarchical structures that are prevalent in human language.This suggests that RNNs’ success might be linked to their ability to model hierarchy. However, a closer inspection of hewitt-etal-2020-rnns construction shows that it is not inherently limited to hierarchical structures. This poses a natural question: What other classes of LMs RNNs can efficiently represent? To this end, we generalize Hewitt et al.’s (2020) construction and show that RNNs can efficiently represent a larger class of LMs than previously claimed—specifically, those that can be represented by a pushdown automaton with a bounded stack and a specific stack update function. Altogether, the efficiency of representing this diverse class of LMs with RNN LMs suggests novel interpretations of their inductive bias.
Anthology ID:
2024.findings-acl.244
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4118–4135
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.244/
DOI:
10.18653/v1/2024.findings-acl.244
Bibkey:
Cite (ACL):
Anej Svete, Robin Chan, and Ryan Cotterell. 2024. On Efficiently Representing Regular Languages as RNNs. In Findings of the Association for Computational Linguistics: ACL 2024, pages 4118–4135, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
On Efficiently Representing Regular Languages as RNNs (Svete et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.244.pdf