arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.00799cs.CL
收藏

MWPToolkit:一个基于深度学习的数学应用题解决器的开源框架

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

Xihua University(西华大学);Singapore Management University(新加坡管理大学);East China Normal University(华东师范大学);Tencent AI Lab(腾讯人工智能实验室);Zhejiang University(浙江大学)

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

摘要:

自20世纪60年代以来,开发自动数学应用题(MWP)求解器一直是NLP研究人员的兴趣。在过去的几年里,有越来越多的数据集和基于深度学习的方法被提出来有效地解决MWP。然而,现有的方法大多是基于一个或两个数据集,在不同的配置下各不相同,导致方法之间缺乏统一、标准化、公平和全面的比较。本文介绍了MWPToolkit,第一个开源框架解决MWPs。在MWPToolkit中,我们将现有MWP求解器的过程分解为多个核心组件,并将其模型解耦为高度可重用的模块。我们还提供了一个超参数搜索功能,以提高性能。总的来说,我们实现和比较17 MWP求解器4广泛使用的单方程生成基准和2多方程生成基准。这些功能使我们的MWPToolkit适合研究人员重现先进的基线模型和快速开发新的MWP求解器。代码和文档可在https://github.com/LYH-YF/MWPToolkit上获得。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑