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

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/

References in corpus (2)

• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Robust Understanding of Word Problems with Extraneous Information

Cited by in corpus (11)

• Graph Neural Networks for Natural Language Processing: A Survey
• Generative Language Modeling for Automated Theorem Proving
• Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning models
• Training Verifiers to Solve Math Word Problems
• Solving Arithmetic Word Problems by Scoring Equations with Recursive Neural Networks
• Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning
• Towards Question Format Independent Numerical Reasoning: A Set of Prerequisite Tasks
• Procedural Reading Comprehension with Attribute-Aware Context Flow
• Mathematical Word Problem Generation from Commonsense Knowledge Graph and Equations
• Towards Tractable Mathematical Reasoning: Challenges, Strategies, and Opportunities for Solving Math Word Problems
• Extracting the Unknown from Long Math Problems