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

By Yihuai Lan, Lei Wang, Qiyuan Zhang, Yunshi Lan, Bing Tian Dai, Yan Wang, Dongxiang Zhang, Ee-Peng Lim. 2021

79 citations recorded by the source corpus.

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

Subfields: Natural Language Processing, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Denny Zhou
2. Jason Wei
3. Dale Schuurmans
4. Ed H. Chi
5. Xuezhi Wang
6. Wei Dang Lu
7. Chang Zhou
8. Dale Schuurmans

In Evaluation & Benchmarks

1. Denny Zhou
2. Jason Wei
3. Wei Dang Lu
4. Chang Zhou
5. Dale Schuurmans
6. Cheng Li
7. Chuanqi Tan
8. Ed H. Chi

Citations in the corpus

• Chain of Thought Prompting Elicits Reasoning in Large Language Models (2022, neutral): “, 2019), c: relevance classifier (Roy & Roth, 2015), d: GPT-2 finetuned with k-fold CV (Lan et al., 2021), e: LCA operation classifier (Roy & Roth, 2015), f : GPT-3 175B with calculator finetuned on 500 examples (Cobbe et al.”
• Self-Consistency Improves Chain of Thought Reasoning in Language Models (2022, methodology): “The supervised baselines are obtained from: a: Relevance and LCA operation classifier (Roy & Roth, 2015), b: GPT-2 finetuned with k-fold CV (Lan et al., 2021), c: Ling et al.”
• Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction (2022, methodology): “Lan et al. (2021) presented two seq2seq models that use BERT/Roberta as both encoder and decoder, namely, BERT-BERT and Roberta-Roberta .”
• Scaling Relationship on Learning Mathematical Reasoning with Large Language Models (2023, methodology): “…on the reasoning tasks of math word problems (MWP), and methods are evaluated on the benchmarks spanning different levels of MWPs (Koncel-Kedziorski et al. (2016); Patel et al. (2021); Lan et al. (2021); Cobbe et al. (2021); Jie et al. (2022); Yuan et al. (2023a); Fu et al. (2023a), inter alia).”
• Solving Linear Algebra by Program Synthesis (2021, methodology): “Techniques have included sequence-tosequence and graph-to-tree Transformers which achieve around 80% on Math23k and MAWPS datasets (Koncel-Kedziorski et al., 2016; Li et al., 2019; Wang et al., 2019; Zhang et al., 2020; Li et al., 2020; Wu et al., 2020; Qin et al., 2020; Lan et al., 2021).”