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

• DOI: 10.1609/aaai.v36i11.21723
• Publication Date: 2022-07-04T10:17:09Z
• Authors: Yihuai Lan; Lei Wang; Qiyuan Zhang; Yunshi Lan; Bing Tian Dai; Yan Wang; Dongxiang Zhang; Ee-Peng Lim
• Keywords: Code (set theory)

While Math Word Problem (MWP) solving has emerged as a popular field of study and made great progress in recent years, most existing methods are benchmarked solely on one or two datasets implemented with different configurations. In this paper, we introduce the first open-source library for MWPs called MWPToolkit, which provides unified, comprehensive, extensible framework research purpose. Specifically, deploy 17 deep learning-based MWP solvers 6 our toolkit. These advanced models solving, covering categories Seq2seq, Seq2Tree, Graph2Tree, Pre-trained Language Models. And these that commonly used benchmarks work. Our toolkit is featured highly modularized reusable components, can help researchers quickly get started develop their own models. We have released code documentation MWPToolkit https://github.com/LYH-YF/MWPToolkit.