On Efficiently Representing Regular Languages as RNNs


Loading...

Date

2024-07

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

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 et al.'s (2020) 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.

Publication status

published

Book title

Findings of the Association for Computational Linguistics: ACL 2024

Journal / series

Volume

Pages / Article No.

4118 - 4135

Publisher

Association for Computational Linguistics

Event

62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

Notes

Funding

204667 - The Forgotten Role of Inductive Bias in Interpretability Research in NLP (SNF)

Related publications and datasets