Tree-structured Decoding for Solving Math Word Problems
Tree-structured Decoding for Solving Math Word Problems
复制标题
DOI：
10.18653/v1/d19-1241
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Qianying Liu;Wenyv Guan;Sujian Li;Daisuke Kawahara
中科院分区：
文献类型：
--
作者：
Qianying Liu;Wenyv Guan;Sujian Li;Daisuke Kawahara
自动解决数学应用题是一个有趣的研究课题，需要连接自然语言描述和形式化数学方程。以前的研究引入了端到端神经网络方法，但这些方法没有有效地考虑方程的一个重要特性，即，抽象语法树为了解决这个问题，我们提出了一种树结构的解码方法，生成的抽象语法树的方程在一个自顶向下的方式。此外，我们的方法可以在解码过程中自动停止，而无需冗余的停止令牌。实验结果表明，我们的方法在Math23K上实现了最先进的单模型性能，Math23K是该任务中最大的数据集。
Automatically solving math word problems is an interesting research topic that needs to bridge natural language descriptions and formal math equations. Previous studies introduced end-to-end neural network methods, but these approaches did not efficiently consider an important characteristic of the equation, i.e., an abstract syntax tree. To address this problem, we propose a tree-structured decoding method that generates the abstract syntax tree of the equation in a top-down manner. In addition, our approach can automatically stop during decoding without a redundant stop token. The experimental results show that our method achieves single model state-of-the-art performance on Math23K, which is the largest dataset on this task.