MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms

TL;DR

This paper presents MathQA, a large dataset of math word problems with detailed operational annotations, and an interpretable neural solver that improves performance and transparency over previous models.

Contribution

Introduction of MathQA, a comprehensive dataset with operational programs, and a neural sequence-to-program model with problem categorization for better interpretability.

Findings

Improved performance over baselines on MathQA and AQuA datasets.

Significant gap remains between model and human performance.

Dataset challenges future research in interpretable math problem solving.

Abstract

We introduce a large-scale dataset of math word problems and an interpretable neural math problem solver that learns to map problems to operation programs. Due to annotation challenges, current datasets in this domain have been either relatively small in scale or did not offer precise operational annotations over diverse problem types. We introduce a new representation language to model precise operation programs corresponding to each math problem that aim to improve both the performance and the interpretability of the learned models. Using this representation language, our new dataset, MathQA, significantly enhances the AQuA dataset with fully-specified operational programs. We additionally introduce a neural sequence-to-program model enhanced with automatic problem categorization. Our experiments show improvements over competitive baselines in our MathQA as well as the AQuA dataset. The results are still significantly lower than human performance indicating that the dataset poses new challenges for future research. Our dataset is available at: https://math-qa.github.io/math-QA/