A Cognitive Regularizer for Language Modeling

Jason Wei, Clara Meister, Ryan Cotterell


Abstract
The uniform information density (UID) hypothesis, which posits that speakers behaving optimally tend to distribute information uniformly across a linguistic signal, has gained traction in psycholinguistics as an explanation for certain syntactic, morphological, and prosodic choices. In this work, we explore whether the UID hypothesis can be operationalized as an inductive bias for statistical language modeling. Specifically, we augment the canonical MLE objective for training language models with a regularizer that encodes UID. In experiments on ten languages spanning five language families, we find that using UID regularization consistently improves perplexity in language models, having a larger effect when training data is limited. Moreover, via an analysis of generated sequences, we find that UID-regularized language models have other desirable properties, e.g., they generate text that is more lexically diverse. Our results not only suggest that UID is a reasonable inductive bias for language modeling, but also provide an alternative validation of the UID hypothesis using modern-day NLP tools.
Anthology ID:
2021.acl-long.404
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5191–5202
Language:
URL:
https://aclanthology.org/2021.acl-long.404
DOI:
10.18653/v1/2021.acl-long.404
Bibkey:
Cite (ACL):
Jason Wei, Clara Meister, and Ryan Cotterell. 2021. A Cognitive Regularizer for Language Modeling. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 5191–5202, Online. Association for Computational Linguistics.
Cite (Informal):
A Cognitive Regularizer for Language Modeling (Wei et al., ACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.404.pdf
Video:
 https://aclanthology.org/2021.acl-long.404.mp4
Data
Wiki-40BWikiText-103WikiText-2