Structure-Unified M-Tree Coding Solver for MathWord Problem

TL;DR

The paper introduces SUMC-Solver, a novel approach that unifies diverse mathematical expression structures in math word problem solving using M-tree coding, improving accuracy especially in low-resource scenarios.

Contribution

It proposes a unified M-tree coding framework and seq2code model for better handling diverse expression structures in math word problems.

Findings

Outperforms state-of-the-art models on MAWPS and Math23K datasets.

Achieves better results under low-resource conditions.

Demonstrates the effectiveness of M-tree coding in MWP solving.

Abstract

As one of the challenging NLP tasks, designing math word problem (MWP) solvers has attracted increasing research attention for the past few years. In previous work, models designed by taking into account the properties of the binary tree structure of mathematical expressions at the output side have achieved better performance. However, the expressions corresponding to a MWP are often diverse (e.g., $n_1+n_2 \times n_3-n_4$, $n_3\times n_2-n_4+n_1$, etc.), and so are the corresponding binary trees, which creates difficulties in model learning due to the non-deterministic output space. In this paper, we propose the Structure-Unified M-Tree Coding Solver (SUMC-Solver), which applies a tree with any M branches (M-tree) to unify the output structures. To learn the M-tree, we use a mapping to convert the M-tree into the M-tree codes, where codes store the information of the paths from tree root to leaf nodes and the information of leaf nodes themselves, and then devise a Sequence-to-Code (seq2code) model to generate the codes. Experimental results on the widely used MAWPS and Math23K datasets have demonstrated that SUMC-Solver not only outperforms several state-of-the-art models under similar experimental settings but also performs much better under low-resource conditions.