论文标题
通过与符号库绑架结合来增强神经数学推理
Enhancing Neural Mathematical Reasoning by Abductive Combination with Symbolic Library
论文作者
论文摘要
最近，数学推理被视为神经系统的艰巨挑战。包括表达翻译，逻辑推理和数学知识获取的能力似乎对于克服挑战至关重要。本文表明，通过与已通过人类知识编程的离散系统绑架组合可以实现某些能力。在数学推理数据集上，我们采用了最近提出的绑架学习框架，并提出了将变压器神经模型与符号数学库相结合的ABL-SYM算法。 ABL-SYM在插值任务上显示出9.73％的精度提高，而在最新方法上，外推任务的精度提高了47.22％。在线演示：http：//math.polixir.ai
Mathematical reasoning recently has been shown as a hard challenge for neural systems. Abilities including expression translation, logical reasoning, and mathematics knowledge acquiring appear to be essential to overcome the challenge. This paper demonstrates that some abilities can be achieved through abductive combination with discrete systems that have been programmed with human knowledge. On a mathematical reasoning dataset, we adopt the recently proposed abductive learning framework, and propose the ABL-Sym algorithm that combines the Transformer neural models with a symbolic mathematics library. ABL-Sym shows 9.73% accuracy improvement on the interpolation tasks and 47.22% accuracy improvement on the extrapolation tasks, over the state-of-the-art approaches. Online demonstration: http://math.polixir.ai
