Lower Bounds on the Expressivity of Recurrent Neural Language Models

Anej Svete, Franz Nowak, Anisha Sahabdeen, Ryan Cotterell


Abstract
The recent successes and spread of large neural language models (LMs) call for a thorough understanding of their abilities. Describing their abilities through LMs’ representational capacity is a lively area of research. Investigations of the representational capacity of neural LMs have predominantly focused on their ability to recognize formal languages. For example, recurrent neural networks (RNNs) as classifiers are tightly linked to regular languages, i.e., languages defined by finite-state automata (FSAs). Such results, however, fall short of describing the capabilities of RNN language models (LMs), which are definitionally distributions over strings. We take a fresh look at the represen- tational capacity of RNN LMs by connecting them to probabilistic FSAs and demonstrate that RNN LMs with linearly bounded precision can express arbitrary regular LMs.
Anthology ID:
2024.naacl-long.380
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6820–6840
Language:
URL:
https://aclanthology.org/2024.naacl-long.380
DOI:
Bibkey:
Cite (ACL):
Anej Svete, Franz Nowak, Anisha Sahabdeen, and Ryan Cotterell. 2024. Lower Bounds on the Expressivity of Recurrent Neural Language Models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 6820–6840, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Lower Bounds on the Expressivity of Recurrent Neural Language Models (Svete et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.380.pdf
Copyright:
 2024.naacl-long.380.copyright.pdf