Laying Anchors: Semantically Priming Numerals in Language Modeling

Mandar Sharma, Rutuja Taware, Pravesh Koirala, Nikhil Muralidhar, Naren Ramakrishnan


Abstract
Off-the-shelf pre-trained language models have become the de facto standard in NLP pipelines for a multitude of downstream tasks. However, the inability of these models to properly encode numerals limits their performance on tasks requiring numeric comprehension. We introduce strategies to semantically prime numerals in any corpus by generating anchors governed by the distribution of numerals in said corpus, thereby enabling mathematically grounded representations of these numeral tokens. We establish the superiority of our proposed techniques through evaluation on a range of numeracy tasks for both in-domain (seen) and out-domain (unseen) numerals. Further, we expand our empirical evaluations to numerals ranging from 1 to 10 billion, a significantly broader range compared to previous studies of the same nature, and we demonstrate significant improvements in the mathematical grounding of our learned embeddings.
Anthology ID:
2024.findings-naacl.169
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2653–2660
Language:
URL:
https://aclanthology.org/2024.findings-naacl.169
DOI:
Bibkey:
Cite (ACL):
Mandar Sharma, Rutuja Taware, Pravesh Koirala, Nikhil Muralidhar, and Naren Ramakrishnan. 2024. Laying Anchors: Semantically Priming Numerals in Language Modeling. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 2653–2660, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Laying Anchors: Semantically Priming Numerals in Language Modeling (Sharma et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.169.pdf
Copyright:
 2024.findings-naacl.169.copyright.pdf