MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers

TL;DR

MWPToolkit is an open-source framework that standardizes, compares, and accelerates the development of deep learning-based math word problem solvers across multiple datasets and models.

Contribution

It introduces a modular, reusable, and comprehensive toolkit for MWP solving, enabling fair benchmarking and rapid development of new methods.

Findings

Implemented and compared 17 MWP solvers

Evaluated on 6 benchmark datasets

Facilitated reproducibility and development

Abstract

Developing automatic Math Word Problem (MWP) solvers has been an interest of NLP researchers since the 1960s. Over the last few years, there are a growing number of datasets and deep learning-based methods proposed for effectively solving MWPs. However, most existing methods are benchmarked soly on one or two datasets, varying in different configurations, which leads to a lack of unified, standardized, fair, and comprehensive comparison between methods. This paper presents MWPToolkit, the first open-source framework for solving MWPs. In MWPToolkit, we decompose the procedure of existing MWP solvers into multiple core components and decouple their models into highly reusable modules. We also provide a hyper-parameter search function to boost the performance. In total, we implement and compare 17 MWP solvers on 4 widely-used single equation generation benchmarks and 2 multiple equations generation benchmarks. These features enable our MWPToolkit to be suitable for researchers to reproduce advanced baseline models and develop new MWP solvers quickly. Code and documents are available at https://github.com/LYH-YF/MWPToolkit.