Enhancing Neural Mathematical Reasoning by Abductive Combination with Symbolic Library

TL;DR

This paper introduces ABL-Sym, a hybrid approach combining neural transformers with symbolic mathematics to improve mathematical reasoning accuracy, especially in extrapolation tasks.

Contribution

It presents the ABL-Sym algorithm that integrates neural and symbolic systems, achieving significant accuracy improvements on mathematical reasoning tasks.

Findings

9.73% accuracy improvement on interpolation tasks

47.22% accuracy improvement on extrapolation tasks

Effective combination of neural and symbolic methods

Abstract

Mathematical reasoning recently has been shown as a hard challenge for neural systems. Abilities including expression translation, logical reasoning, and mathematics knowledge acquiring appear to be essential to overcome the challenge. This paper demonstrates that some abilities can be achieved through abductive combination with discrete systems that have been programmed with human knowledge. On a mathematical reasoning dataset, we adopt the recently proposed abductive learning framework, and propose the ABL-Sym algorithm that combines the Transformer neural models with a symbolic mathematics library. ABL-Sym shows 9.73% accuracy improvement on the interpolation tasks and 47.22% accuracy improvement on the extrapolation tasks, over the state-of-the-art approaches. Online demonstration: http://math.polixir.ai