论文标题
寻求多种推理逻辑：解决数学单词问题的受控方程式表达生成
Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems
论文作者
论文摘要
为了解决数学单词问题，人类的学生利用了达到不同方程解决方案的各种推理逻辑。但是，自动求解器的主流序列与序列方法旨在解码通过人类注释监督的固定解决方程。在本文中，我们通过利用一组控制代码来指导模型考虑某些推理逻辑并解码从人类参考转换的相应方程式表达式来指导模型来考虑某些推理逻辑并解码相应的方程式表达式，从而提出了一个受控的方程生成求解器。经验结果表明，我们的方法普遍提高了单人（MATH23K）和多个不知名（draw1k，hmwp）基准的性能，在具有挑战性的多重尚不计算的数据集上，高达13.2％的准确性。
To solve Math Word Problems, human students leverage diverse reasoning logic that reaches different possible equation solutions. However, the mainstream sequence-to-sequence approach of automatic solvers aims to decode a fixed solution equation supervised by human annotation. In this paper, we propose a controlled equation generation solver by leveraging a set of control codes to guide the model to consider certain reasoning logic and decode the corresponding equations expressions transformed from the human reference. The empirical results suggest that our method universally improves the performance on single-unknown (Math23K) and multiple-unknown (DRAW1K, HMWP) benchmarks, with substantial improvements up to 13.2% accuracy on the challenging multiple-unknown datasets.
