Solving General Arithmetic Word Problems

TL;DR

This paper introduces a novel algorithmic approach for solving multi-step arithmetic word problems without relying on templates, using expression trees and world knowledge to improve accuracy.

Contribution

It presents the first algorithm capable of handling multi-step arithmetic problems without predefined templates, utilizing expression trees and quantity schemas.

Findings

Outperforms existing systems on benchmark datasets

Achieves state-of-the-art performance in arithmetic problem solving

Uses a novel constrained inference framework

Abstract

This paper presents a novel approach to automatically solving arithmetic word problems. This is the first algorithmic approach that can handle arithmetic problems with multiple steps and operations, without depending on additional annotations or predefined templates. We develop a theory for expression trees that can be used to represent and evaluate the target arithmetic expressions; we use it to uniquely decompose the target arithmetic problem to multiple classification problems; we then compose an expression tree, combining these with world knowledge through a constrained inference framework. Our classifiers gain from the use of {\em quantity schemas} that supports better extraction of features. Experimental results show that our method outperforms existing systems, achieving state of the art performance on benchmark datasets of arithmetic word problems.