Laying Anchors: Semantically Priming Numerals in Language Modeling

arXiv:2404.01536v1 Announce Type: cross
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 …

abstract anchors arxiv become cs.ai cs.cl cs.lg encode however language language models modeling nlp performance pipelines prime standard strategies tasks type