arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.14095cs.AIcs.LG
收藏

浅析Transformers多项式化简能力的细微差别

Analyzing the Nuances of Transformers' Polynomial Simplification Abilities

Microsoft Vancouver(微软温哥华);Microsoft Research India(微软研究院印度)

Vishesh Agarwal, Somak Aditya, Navin Goyal

摘要:

符号数学任务(如积分)通常需要多个定义良好的步骤和对子任务的理解才能获得解决方案。为了以细粒度的方式了解Transformers在此类任务中的能力,我们偏离了传统的端到端设置,并探索逐步多项式简化任务。多项式可以写成一个简单的范式,作为一个和单项式是有序的字典顺序。对于不一定在该范式中的多项式,应用一系列简化步骤以达到完全简化的(即,在范式)多项式中。我们提出了一种合成多项式数据集生成算法,该算法生成具有唯一证明步骤的多项式。通过改变系数配置,输入表示,证明粒度和广泛的超参数调整,我们观察到,Transformers始终与数字乘法斗争。我们探索了两种方法来缓解这一问题:课程学习和符号计算器方法(其中数值运算被卸载到计算器)。这两种方法都提供了基于vanilla Transformers的基线的显著增益。

英文摘要:

Symbolic Mathematical tasks such as integration often require multiple well-defined steps and understanding of sub-tasks to reach a solution. To understand Transformers' abilities in such tasks in a fine-grained manner, we deviate from traditional end-to-end settings, and explore a step-wise polynomial simplification task. Polynomials can be written in a simple normal form as a sum of monomials which are ordered in a lexicographic order. For a polynomial which is not necessarily in this normal form, a sequence of simplification steps is applied to reach the fully simplified (i.e., in the normal form) polynomial. We propose a synthetic Polynomial dataset generation algorithm that generates polynomials with unique proof steps. Through varying coefficient configurations, input representation, proof granularity, and extensive hyper-parameter tuning, we observe that Transformers consistently struggle with numeric multiplication. We explore two ways to mitigate this: Curriculum Learning and a Symbolic Calculator approach (where the numeric operations are offloaded to a calculator). Both approaches provide significant gains over the vanilla Transformers-based baseline.

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。

↑