Learning Mathematical Properties of Integers

09/15/2021
by   Maria Ryskina, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/04/2019

SECNLP: A Survey of Embeddings in Clinical Natural Language Processing

Traditional representations like Bag of words are high dimensional, spar...
research
09/07/2021

ArGoT: A Glossary of Terms extracted from the arXiv

We introduce ArGoT, a data set of mathematical terms extracted from the ...
research
07/05/2023

Deductive Additivity for Planning of Natural Language Proofs

Current natural language systems designed for multi-step claim validatio...
research
05/25/2022

Semantic Embeddings in Semilattices

To represent anything from mathematical concepts to real-world objects, ...
research
02/28/2023

Linear Spaces of Meanings: the Compositional Language of VLMs

We investigate compositional structures in vector data embeddings from p...
research
03/24/2022

Computation of Centroidal Voronoi Tessellations in High Dimensional spaces

Owing to the natural interpretation and various desirable mathematical p...
research
10/08/2022

Semantic Representations of Mathematical Expressions in a Continuous Vector Space

Mathematical notation makes up a large portion of STEM literature, yet, ...

Please sign up or login with your details

Forgot password? Click here to reset