MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers
This provides a unified tool for NLP researchers working on MWP solvers, though it is incremental as it builds on existing methods without introducing new algorithmic breakthroughs.
The paper tackles the lack of standardized comparison in Math Word Problem (MWP) solvers by introducing MWPToolkit, an open-source framework that implements and compares 17 solvers on 6 benchmarks, enabling researchers to reproduce models and develop new solvers quickly.
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.