The Role of n-gram Smoothing in the Age of Neural Networks

Luca Malagutti, Andrius Buinovskij, Anej Svete, Clara Meister, Afra Amini, Ryan Cotterell

Abstract
For nearly three decades, language models derived from the n-gram assumption held the state of the art on the task. The key to their success lay in the application of various smoothing techniques that served to combat overfitting. However, when neural language models toppled n-gram models as the best performers, n-gram smoothing techniques became less relevant. Indeed, it would hardly be an understatement to suggest that the line of inquiry into n-gram smoothing techniques became dormant. This paper re-opens the role classical n-gram smoothing techniques may play in the age of neural language models. First, we draw a formal equivalence between label smoothing, a popular regularization technique for neural language models, and add-𝜆 smoothing. Second, we derive a generalized framework for converting any n-gram smoothing technique into a regularizer compatible with neural language models. Our empirical results find that our novel regularizers are comparable to and, indeed, sometimes outperform label smoothing on language modeling and machine translation.
Anthology ID:
2024.naacl-long.382
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:
6882–6899
Language:
URL:
https://aclanthology.org/2024.naacl-long.382
DOI:
10.18653/v1/2024.naacl-long.382
Bibkey:
Cite (ACL):
Luca Malagutti, Andrius Buinovskij, Anej Svete, Clara Meister, Afra Amini, and Ryan Cotterell. 2024. The Role of n-gram Smoothing in the Age of Neural Networks. 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 6882–6899, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
The Role of n-gram Smoothing in the Age of Neural Networks (Malagutti et al., NAACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2024.naacl-long.382.pdf
PDF Search