English

Learning Mathematical Properties of Integers

Computation and Language 2021-09-16 v1 Machine Learning

Abstract

Embedding words in high-dimensional vector spaces has proven valuable in many natural language applications. In this work, we investigate whether similarly-trained embeddings of integers can capture concepts that are useful for mathematical applications. We probe the integer embeddings for mathematical knowledge, apply them to a set of numerical reasoning tasks, and show that by learning the representations from mathematical sequence data, we can substantially improve over number embeddings learned from English text corpora.

Keywords

Cite

@article{arxiv.2109.07230,
  title  = {Learning Mathematical Properties of Integers},
  author = {Maria Ryskina and Kevin Knight},
  journal= {arXiv preprint arXiv:2109.07230},
  year   = {2021}
}

Comments

BlackboxNLP 2021

R2 v1 2026-06-24T05:59:05.968Z