Tackling Math Word Problems with Fine-to-Coarse Abstracting and Reasoning

TL;DR

This paper introduces a novel fine-to-coarse reasoning approach for solving math word problems, capturing both local details and global structure to improve generalization and accuracy.

Contribution

It proposes a bottom-up reasoning model that iteratively combines operands to better understand and solve math word problems, surpassing previous global-focused methods.

Findings

Achieves higher accuracy on Math23k and SVAMP datasets.

Demonstrates improved generalization to unseen problem types.

Shows robustness over existing Seq2Seq and Seq2Tree models.

Abstract

Math Word Problems (MWP) is an important task that requires the ability of understanding and reasoning over mathematical text. Existing approaches mostly formalize it as a generation task by adopting Seq2Seq or Seq2Tree models to encode an input math problem in natural language as a global representation and generate the output mathematical expression. Such approaches only learn shallow heuristics and fail to capture fine-grained variations in inputs. In this paper, we propose to model a math word problem in a fine-to-coarse manner to capture both the local fine-grained information and the global logical structure of it. Instead of generating a complete equation sequence or expression tree from the global features, we iteratively combine low-level operands to predict a higher-level operator, abstracting the problem and reasoning about the solving operators from bottom to up. Our model is naturally more sensitive to local variations and can better generalize to unseen problem types. Extensive evaluations on Math23k and SVAMP datasets demonstrate the accuracy and robustness of our method.