GraphMR: Graph Neural Network for Mathematical Reasoning
GraphMR: Graph Neural Network for Mathematical Reasoning
复制标题
DOI：
10.18653/v1/2021.emnlp-main.273
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Weijie Feng;Binbin Liu;Dongpeng Xu;Qilong Zheng;Yun Xu
中科院分区：
文献类型：
--
作者：
Weijie Feng;Binbin Liu;Dongpeng Xu;Qilong Zheng;Yun Xu
数学推理的目的是根据给定的数学问题，推断出可满足的解。先前的自然语言处理研究已经证明了序列到序列（Seq2Seq）或相关变体在数学求解中的有效性。然而，很少有作品能够探索隐藏在表达式中的结构或句法信息（例如，优先级和结合性）。本论文着手研究这些未开发的信息对神经结构的有用性。首先，在语法分析中，数学问题以图形的形式表示。图的结构化性质允许它们表示变量或运算符的关系，同时保留表达式的语义。在转换到新的表示之后，我们提出了一个图到序列神经网络GraphMR，它可以有效地学习图输入的层次信息来解决数学问题和推测答案。构建了一个包含4类数学任务和3条Seq2Seq基线的完整实验场景进行综合分析，结果表明GraphMR在隐藏信息学习和数学解析方面优于其他算法。
Mathematical reasoning aims to infer satisfiable solutions based on the given mathematics questions. Previous natural language processing researches have proven the effectiveness of sequence-to-sequence (Seq2Seq) or related variants on mathematics solving. However, few works have been able to explore structural or syntactic information hidden in expressions (e.g., precedence and associativity). This dissertation set out to investigate the usefulness of such untapped information for neural architectures. Firstly, mathematical questions are represented in the format of graphs within syntax analysis. The structured nature of graphs allows them to represent relations of variables or operators while preserving the semantics of the expressions. Having transformed to the new representations, we proposed a graph-to-sequence neural network GraphMR, which can effectively learn the hierarchical information of graphs inputs to solve mathematics and speculate answers. A complete experimental scenario with four classes of mathematical tasks and three Seq2Seq baselines is built to conduct a comprehensive analysis, and results show that GraphMR outperforms others in hidden information learning and mathematics resolving.