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 2203.14487cs.LGcs.AI
收藏

基于符号库的溯因组合增强神经数学推理

Enhancing Neural Mathematical Reasoning by Abductive Combination with Symbolic Library

Nanjing University(南京大学);Polixir Technologies(智谱科技)

Yangyang Hu, Yang Yu

摘要:

近年来,数学推理已被证明是对神经系统的一个严峻挑战。包括表达翻译,逻辑推理和数学知识获取在内的能力似乎是克服挑战所必需的。本文证明了一些能力可以通过溯因组合与离散系统,已编程与人类知识。在一个数学推理数据集上,我们采用最近提出的溯因学习框架,提出了结合Transformer神经模型和符号数学库的ABL-Sym算法。ABL-Sym在插值任务上显示出9.73%的精度提高,在外推任务上显示出47.22%的精度提高,超过了最先进的方法。在线演示:http://math.polixir.ai

英文摘要:

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

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。

↑