Translating a Math Word Problem to an Expression Tree
This work improves automated math problem-solving for educational applications, though it is incremental as it builds on existing SEQ2SEQ methods.
The authors tackled the non-determinism in math word problem solving by normalizing equations to unique expression trees and combining three SEQ2SEQ models into an ensemble, achieving state-of-the-art performance on the Math23K dataset.
Sequence-to-sequence (SEQ2SEQ) models have been successfully applied to automatic math word problem solving. Despite its simplicity, a drawback still remains: a math word problem can be correctly solved by more than one equations. This non-deterministic transduction harms the performance of maximum likelihood estimation. In this paper, by considering the uniqueness of expression tree, we propose an equation normalization method to normalize the duplicated equations. Moreover, we analyze the performance of three popular SEQ2SEQ models on the math word problem solving. We find that each model has its own specialty in solving problems, consequently an ensemble model is then proposed to combine their advantages. Experiments on dataset Math23K show that the ensemble model with equation normalization significantly outperforms the previous state-of-the-art methods.