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 2106.00990cs.AI
收藏

序列到一般树:知识引导的几何应用题求解

Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving

Institute of Information Science, Academia Sinica(中央研究院资讯科学研究所)

Shih-hung Tsai, Chao-Chun Liang, Hsin-Min Wang, Keh-Yih Su

摘要:

随着深度学习的最新进展,神经求解器在解决数学应用题方面取得了可喜的成果。但是,这些SOTA求解器只生成包含基本算术运算符的二进制表达式树,而不显式使用数学公式。因此,它们生成的表达式树很长且无法解释,因为它们需要使用多个运算符和常量来表示一个公式。在本文中,我们提出了序列到一般树(S2G),学习生成可解释和可执行的操作树,其中节点可以是具有任意数量参数的公式。现在允许节点是公式,S2G可以学习将数学领域知识融入到解决问题中,使结果更具可解释性。实验表明,S2G可以实现更好的性能对强基线的问题,需要领域知识。

英文摘要:

With the recent advancements in deep learning, neural solvers have gained promising results in solving math word problems. However, these SOTA solvers only generate binary expression trees that contain basic arithmetic operators and do not explicitly use the math formulas. As a result, the expression trees they produce are lengthy and uninterpretable because they need to use multiple operators and constants to represent one single formula. In this paper, we propose sequence-to-general tree (S2G) that learns to generate interpretable and executable operation trees where the nodes can be formulas with an arbitrary number of arguments. With nodes now allowed to be formulas, S2G can learn to incorporate mathematical domain knowledge into problem-solving, making the results more interpretable. Experiments show that S2G can achieve a better performance against strong baselines on problems that require domain knowledge.

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。

↑