arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.07017cs.CL
收藏

ComSearch:求解弱监督数学应用题的组合策略方程搜索

ComSearch: Equation Searching with Combinatorial Strategy for Solving Math Word Problems with Weak Supervision

Graduate School of Informatics, Kyoto University(京都大学信息学研究科);Xiaomi AI Lab(小米人工智能实验室);Peking University(北京大学)

Qianying Liu, Wenyu Guan, Jianhao Shen, Fei Cheng, Sadao Kurohashi

摘要:

以往的研究已经引入了一个弱监督的范式来解决数学应用题,只需要答案值注释。当这些方法搜索作为伪标签的正确值方程候选时,它们在巨大的方程空间的狭窄子空间中搜索。为了解决这个问题,我们提出了一种新的搜索算法与组合策略\textbf{ComSearch},它可以压缩搜索空间,排除数学等价方程。压缩允许搜索算法枚举所有可能的方程并获得高质量的数据。我们研究了伪标签中包含错误数学逻辑的噪声,我们称之为\textit{false-matching}问题,并提出了一个排序模型来消除伪标签。我们的方法拥有一个灵活的框架,利用现有的两个有监督的数学单词问题求解器训练伪标签,并在弱监督任务中实现最先进的性能。

英文摘要:

Previous studies have introduced a weakly-supervised paradigm for solving math word problems requiring only the answer value annotation. While these methods search for correct value equation candidates as pseudo labels, they search among a narrow sub-space of the enormous equation space. To address this problem, we propose a novel search algorithm with combinatorial strategy \textbf{ComSearch}, which can compress the search space by excluding mathematically equivalent equations. The compression allows the searching algorithm to enumerate all possible equations and obtain high-quality data. We investigate the noise in the pseudo labels that hold wrong mathematical logic, which we refer to as the \textit{false-matching} problem, and propose a ranking model to denoise the pseudo labels. Our approach holds a flexible framework to utilize two existing supervised math word problem solvers to train pseudo labels, and both achieve state-of-the-art performance in the weak supervision task.

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。

↑